Google LLC patent applications published on November 2nd, 2023

Patent applications for Google LLC on November 2nd, 2023

CONTACTLESS DEVICE FOR RESPIRATORY HEALTH MONITORING (18023328)

Main Inventor

Dongeek Shin

Brief explanation

The patent application describes a contactless health monitoring device that uses radar technology to monitor a user's breathing.

• The device performs a beam steering process to create multiple radar data streams from the received radar data.
• It determines the user's breathing displacement over time for each spatial zone radar data stream.
• The device analyzes the breathing displacement data for each spatial zone to assess the user's breathing patterns.
• Based on this analysis, the device provides a screening result, which could indicate any abnormalities or issues with the user's breathing.

Abstract

A contactless health monitoring device may perform a beam steering process that creates a plurality of beam-steered radar data streams from the received radar data stream. The contactless health monitoring device may determine breathing displacement for a user in relation to time for each spatial zone radar data stream. The contactless health monitoring device may analyze the breathing displacement for the user in relation to time for each spatial zone radar data stream. The contactless health monitoring device may output a screening result based on analyzing the breathing displacement for the user.

Transforming Scale Ring (18220382)

Main Inventor

Su Chuin Leong

Brief explanation

The patent application describes a method for providing a map scale using a computing device.

• The method involves displaying a geographic area on a device's display.
• It receives information about a specific location within the geographic area.
• In response to this information, it generates a scale with two graphics surrounding the location.
• The distance between the two graphics is calculated.
• A reference value is provided on the display, which can be either a time or distance to travel between the two graphics.
• The reference value is based on the calculated distance.

Abstract

A method for providing a map scale, using a computing device having one or more processors, comprising providing a geographic area for display on a display of a device, receiving information corresponding to a first input associated with a geographic location within the geographic area, providing, in response to the information and for display on the display, a scale including a first graphic and a second graphic surrounding the geographic location, calculating a distance between the first graphic and the second graphic, and providing a reference value for display on the display, the reference value including at least one of a time or distance to travel between the first and second graphics of the scale, the time or distance to travel being based on the calculated distance.

FINGERTIP TRACKING USING RADAR (17661401)

Main Inventor

Anandghan Waghmare

Brief explanation

The patent application describes a method involving the use of a peripheral device and a wearable device to track movement and communicate corresponding information. Here is a simplified explanation of the abstract:

• The peripheral device, which is connected to the wearable device, sends out a frequency-modulated continuous wave (FMCW) signal.
• The peripheral device receives a reflected signal based on the FMCW signal.
• By analyzing the reflected signal, the peripheral device tracks the movement associated with the peripheral device.
• The peripheral device then communicates the information about the movement to the wearable device.

Bullet points explaining the patent/innovation:

• The method involves using a peripheral device and a wearable device to track movement.
• The peripheral device sends out a frequency-modulated continuous wave (FMCW) signal.
• The peripheral device receives a reflected signal based on the FMCW signal.
• By analyzing the reflected signal, the peripheral device can track its own movement.
• The peripheral device communicates the information about its movement to the wearable device.
• This method can be used in various applications such as fitness tracking, virtual reality, or motion sensing devices.
• The use of FMCW signals allows for accurate and real-time tracking of movement.
• The communication between the peripheral device and the wearable device enables seamless integration and data sharing.

Abstract

A method including transmitting, by a peripheral device communicatively coupled to a wearable device, a frequency-modulated continuous wave (FMCW), receiving, by the peripheral device, a reflected signal based on the FMCW, tracking, by the peripheral device, a movement associated with the peripheral device based on the reflected signal, and communicating, from the peripheral device to the wearable device, an information corresponding to the movement associated with the peripheral device.

Detecting User Presence (17639545)

Main Inventor

Octavio Ponce Madrigal

Brief explanation

- The patent application describes techniques and apparatuses for an ultrasonic sensor that can detect user presence.

- The sensor does not rely on time-of-flight techniques to determine user presence. - User presence can be detected by occluding receiving or transmitting transducers, or by detecting a change in the noise floor of the transducers. - This allows the sensor to continue detecting user presence even if the user blocks one or more transducers. - The ultrasonic sensor can also control other components in a computing device based on user presence, improving the user experience and power management.

Abstract

Techniques and apparatuses are described that implement an ultrasonic sensor capable of detecting user presence. This ultrasonic sensor can detect user presence without relying on time-of-flight techniques. In particular, the ultrasonic sensor can determine that a user is present based on the occlusion of at least one receiving transducer (e.g., microphone occlusion), the occlusion of at least one transmitting transducer (e.g., speaker occlusion), or a detected change in an audible noise floor of at least one transducer. In this way, the ultrasonic sensor can continue to detect user presence in situations in which a user occludes one or more transducers of the ultrasonic sensor. The ultrasonic sensor can also control operation of another component within a computing device based on the presence of the user to improve the user experience and/or improve power management.

ENCODING/DECODING USER INTERFACE INTERACTIONS (18347374)

Main Inventor

Keun Soo Yim

Brief explanation

- The patent application describes a method for encoding and decoding user interface interactions.

- The method involves receiving a query from a user through an assistant-enabled device. - The query includes the user's intent for interacting with an application. - The method obtains a set of categorized actions for the application. - Each categorized action is associated with one or more parameters and represents a high-level description of the user's intent. - For each categorized action, the method selects a script that performs low-level interactions with the application. - The selected script is executed to represent the user's intent for interacting with the application.

Abstract

A method of encoding and decoding user interface interactions includes receiving a query from a user captured by an assistant-enabled device associated with the user. The query includes a user intent for interacting with an application. The method includes obtaining, for the application, a set of categorized actions. Each categorized action of the set of categorized actions is associated with one or more parameters and represents a high-level description of the user intent of the user interacting with the application. For each respective categorized action of the set of categorized actions, the method includes selecting a respective script associated with the respective categorized action that performs one or more low-level interactions with the application and executing the respective script to represent the user intent for interacting with the application.

ULTRASONIC DEVICE-TO-DEVICE COMMUNICATION FOR WEARABLE DEVICES (18349445)

Main Inventor

Kevin Howard Orr

Brief explanation

- The patent application describes a system and method for transmitting ultrasound signals between wearable computing devices.

- The first wearable computing device sends a first ultrasound signal, and the second wearable computing device receives a second ultrasound signal in response. - The first wearable computing device uses the time-of-flight of the ultrasound signal to determine the location of the second wearable computing device. - Based on this location information, a wireless connection is established between the two devices. - The wireless connection is established using the identifier and location associated with the second wearable computing device.

Abstract

Systems and methods are described that can include transmitting, from a first wearable computing device, a first ultrasound signal and receiving, by the first wearable computing device and responsive to the first ultrasound signal, a second ultrasound signal from a second wearable computing device. The method can include identifying, by the first wearable computing device, a location of the second wearable computing device with respect to a location of the first wearable computing device where the location of the second wearable computing device can be identified based on a determined time-of-flight of the first ultrasound signal. The method can include establishing a wireless connection between the first wearable computing device and the second wearable computing device where the wireless connection can be based at least in part on the identifier and the identified location associated with the second wearable computing device.

NO-CODING MACHINE LEARNING PIPELINE (18348623)

Main Inventor

Jiaqi Guo

Brief explanation

The patent application describes methods, systems, and computer programs for generating machine learning models.

• The methods involve receiving user selection of a mode button through a graphical user interface (GUI).
• When the mode button is selected, the GUI displays a first set of user-selectable buttons corresponding to machine learning routines.
• When the mode button is not selected, the GUI displays a second set of user-selectable buttons corresponding to machine learning sub-routines.
• Upon receiving user selection of the mode button, the first set of user-selectable buttons is displayed.
• The user can then select one or more of the first set of user-selectable buttons.
• A graphical representation of a machine learning model defined by the selected buttons is displayed.
• Finally, a file representing the machine learning model is generated.

Abstract

Methods, and systems, including computer programs encoded on computer storage media for generating machine learning models. A method includes receiving, through a GUI, user selection of a mode button displayed in the GUI, wherein the mode button, when selected, causes the GUI to display a first set of user-selectable buttons that correspond to respective machine learning routines, and when not selected, causes the GUI to display a second set of user-selectable buttons that correspond to respective machine learning sub-routines; in response to receiving user selection of the mode button, displaying the first set of user-selectable buttons; receiving user selection of one or more of the first set of user-selectable buttons; displaying a graphical representation of a machine learning model defined by machine learning routines corresponding to the user selected one or more of the first set of user-selectable buttons and generating a file representing the machine learning model.

CREATING USER INTERFACE USING MACHINE LEARNING (18348191)

Main Inventor

Zifeng Huang

Brief explanation

- This patent application is about methods, systems, and apparatus for training and using machine learning models to generate graphical user interfaces (GUIs) from textual descriptions.

- The invention involves computer programs encoded on a computer storage medium. - The purpose is to simplify the process of creating GUIs by using machine learning techniques. - The invention aims to generate GUIs based on textual descriptions, eliminating the need for manual design. - The patent application covers both the training of machine learning models for GUI generation and the actual usage of these models. - The invention can be implemented using computer programs stored on a computer storage medium. - The innovation has potential applications in various industries where GUIs are used, such as software development and user interface design.

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training and using machine learning models to generate graphical user interfaces from textual descriptions.

Shared Compilation Cache Verification System (18338023)

Main Inventor

Hyo Jun Kim

Brief explanation

The abstract describes a computer-implemented method for verifying a shared cache in a simplified manner. 

• The method involves retrieving a precompiled shared cache entry corresponding to a shared cache key, which is associated with an operation request.
• It also involves obtaining a directly compiled resource associated with the operation request.
• The method further includes certifying one or more portions of the shared cache by comparing the precompiled shared cache entry with the directly compiled resource.

Abstract

Example embodiments of the present disclosure provide, in one example aspect, an example computer-implemented method for verification of a shared cache. The example method can include retrieving a precompiled shared cache entry corresponding to a shared cache key, the shared cache key being associated with an operation request. The example method can include obtaining a directly compiled resource associated with the operation request. The example method can include certifying one or more portions of the shared cache based at least in part on a comparison of the precompiled shared cache entry and the directly compiled resource.

TRANSLATING LARGE SOURCE CODE USING SPARSE SELF-ATTENTION (17731593)

Main Inventor

Rishabh Singh

Brief explanation

- This patent application describes techniques for translating source code using sparse-self attention.

- The techniques involve processing a source code snippet to obtain graphs representing snippet tokens and their relationships. - From these graphs, a subset of token pairs is identified, which includes snippet tokens connected by edges in the graphs. - A self-attention network of a translation machine learning model is then adapted to sparsely attend across this subset of token pairs. - The adapted model is used to process the source code snippet and generate a translation in a different programming language.

Abstract

Techniques are described herein for translating source code using sparse-self attention. In various implementations, a source code snippet in a first programming language may be processed to obtain graph(s) representing snippet tokens, and relationships therebetween. Based on the graph(s), a subset of snippet token pairs may be identified from a superset of all possible token pairs in the source code snippet. Each token pair of the subset may include snippet tokens that are represented by nodes connected by one or more edges of the one or more graphs. A self-attention network of a translation machine learning model may be adapted to sparsely attend across the identified subset of token pairs. The source code snippet may then be processed based on the adapted translation machine learning model to generate a translation of the source code snippet in the second programming language.

FEATURE EXPOSURE FOR MODEL RECOMMENDATIONS AND FEEDBACK (18217371)

Main Inventor

Ratna S. Desai

Brief explanation

The patent application describes a system for providing user feedback to an action selection model.

• The system includes methods and apparatus for displaying interaction elements for recommendations selected by a selection model.
• Each interaction element can be selected using either a first interaction mode or a second interaction mode.
• Selection using the first interaction mode indicates acceptance of the recommendation described by the interaction element.
• Selection using the second interaction mode causes the user device to display the decision data that led to the selection of the recommendation.
• The recommendations can be actions that a user device can perform or content that a user can consume.
• The system aims to improve user feedback and understanding of the decision-making process behind the recommendations provided by the selection model.

Abstract

Systems, methods and apparatus for providing user feedback to an action selection model. In an aspect, a method includes displaying interaction elements for recommendations selected by a selection model. Each interaction element may be selected by one of a first interaction mode or a second interaction mode. Selection by the first interaction mode indicates an acceptance of the recommendation described the interaction element. Selection by the second interaction mode causes the user device to display the decision data that caused the selection model to select the recommendation described by the interaction element. In some implementations, the recommendations are actions that a user device may perform. In other implementations, each recommendation may be one of an action that the user device may perform or content that a user may consume.

Optimization of Parameters of a System, Product, or Process (18347386)

Main Inventor

Daniel Reuben Golovin

Brief explanation

- The patent application is about computing systems and methods for optimizing adjustable parameters of a system.

- The system uses black-box optimization techniques to suggest new parameter values for evaluation. - The iterative suggestion and evaluation process aims to improve the overall performance of the system. - An objective function is used to evaluate the performance of the system based on one or more metrics. - The patent application introduces a new black-box optimization technique called "Gradientless Descent" that is faster and more clever than random search. - Gradientless Descent retains most of the favorable qualities of random search.

Abstract

The present disclosure provides computing systems and associated methods for optimizing one or more adjustable parameters (e.g. operating parameters) of a system. In particular, the present disclosure provides a parameter optimization system that can perform one or more black-box optimization techniques to iteratively suggest new sets of parameter values for evaluation. The iterative suggestion and evaluation process can serve to optimize or otherwise improve the overall performance of the system, as evaluated by an objective function that evaluates one or more metrics. The present disclosure also provides a novel black-box optimization technique known as “Gradientless Descent” that is more clever and faster than random search yet retains most of random search's favorable qualities.

Mapping Images to Search Queries (18344509)

Main Inventor

Matthew Sharifi

Brief explanation

The patent application describes methods, systems, and apparatus for improving image search queries.

• The invention involves receiving a query image and associated entities.
• It identifies candidate search queries that are pre-associated with the entities.
• A relevance score is generated for each candidate search query.
• The invention selects a representative search query for the query image based on the relevance scores.
• The representative search query is provided as output in response to the query image.

Abstract

Methods, systems, and apparatus for receiving a query image, receiving one or more entities that are associated with the query image, identifying, for one or more of the entities, one or more candidate search queries that are pre-associated with the one or more entities, generating a respective relevance score for each of the candidate search queries, selecting, as a representative search query for the query image, a particular candidate search query based at least on the generated respective relevance scores and providing the representative search query for output in response to receiving the query image.

CLOUD INFERENCE SYSTEM (18350685)

Main Inventor

Emanuel Taropa

Brief explanation

The patent application is about methods, systems, and apparatus for storing and accessing data in a cloud system.

• The invention involves receiving log data that records events and indexing them based on specified event types and group identifiers.
• It allows users to query the indexed data and request predicted events based on a reference parameter.
• The system searches for groups of events associated with the reference parameter and computes the most likely predicted events to co-occur with them.
• The computed predicted events are then provided to the user.

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for storing and accessing data in a cloud system. One of the methods includes receiving an identification of log data that records occurrences of events; receiving a specification of a plurality of different event types to be indexed; indexing the log data according to the specification and group identifiers; receiving a query specifying a reference parameter and requesting one or more predicted events; searching the indexed groups to identify a plurality of groups having events associated with the reference parameter; computing one or more predicted events, from the identified plurality of groups, that are most likely to co-occur in the indexed groups with events associated with the reference parameter; and providing the computed one or more predicted events.

Electronic List User Interface (18347365)

Main Inventor

Shih-Hao Yeh

Brief explanation

The patent application is about a system that processes user inputs for electronic list systems. Here is a simplified explanation of the abstract:

• The system receives user inputs from a device.
• It parses the received user inputs to extract a minimum set of product data.
• The parsed data is used to query shopping services.
• The system receives product descriptions from the queried shopping services.
• It presents the received product descriptions to the user through their device.

Bullet points explaining the patent/innovation:

• The system simplifies the process of searching for products by parsing user inputs and querying shopping services.
• It saves users time and effort by automatically extracting relevant product data from their inputs.
• The system can query multiple shopping services to provide a wider range of product options to the user.
• It presents the product descriptions in a user-friendly manner through the user's device.
• The innovation improves the efficiency and convenience of using electronic list systems for shopping.

Abstract

Processing inputs to electronic list systems. Receiving, from a user device, a user input. Parsing the received user input for a minimum set of product data for querying a shopping service. Upon parsing a minimum set of product data for querying a shopping service, querying at least one shopping service using the parsed data. Receiving, from at least one queried shopping service, at least one product description responsive to the query. Presenting, via the user device, each received at least one product description to the user.

SYSTEMS AND METHODS FOR DISPLAYING MEDIA FILES (18196759)

Main Inventor

Andrew John Gasparovic

Brief explanation

- This patent application describes systems and methods for displaying media files on a device.

- The device has two modes: a first mode that displays a subset of media files based on a user query, and a second mode that displays all media files. - The first mode remains active on the device until it is manually deactivated. - When the user specifies the first mode with a query, the device retrieves a corresponding subset of files from a remote system and displays them sequentially. - If the user does not specify a query, the device retrieves all files from a remote device and displays them sequentially according to the second mode.

Abstract

Systems and methods for displaying media files on a device are provided. The device provides a first mode that displays a subset of media files, determined by a user query, from a plurality of media files. Once activated, the first mode persists on the device prior to becoming inactive. A second mode of the device displays the plurality of media files. The second mode is active when the first mode is inactive. An instruction is received from a user. When the instruction specifies the first mode by inclusion of a user query, a corresponding subset of files is obtained from a remote system. The subset of files is sequentially displayed until the period of time has elapsed according to the first mode. When the instruction does not specify a query, the plurality of files is polled for from a remote device and sequentially displayed according to the second mode.

COMPARATIVE SEARCH WITHIN USER-GENERATED CONTENT (18160839)

Main Inventor

Diego Baron

Brief explanation

- The patent application describes a method for searching within user-generated reviews.

- The method involves receiving a search query from a client device to search within a collection of user-generated reviews related to multiple entities. - The search query is used to identify a set of user-generated reviews that match the search terms. - The set of user-generated reviews includes reviews for two different entities. - The method allows for displaying at least a portion of the reviews for both entities simultaneously on a comparison layout of a user interface.

Abstract

According to an aspect, a method for searching within user-generated reviews includes receiving, from a client device, a search query to search within a plurality of user-generated reviews relating to a plurality of entities, and identifying, in response to the search query, a set of user-generated reviews from the plurality of user-generated reviews that correspond to one or more search terms of the search query, where the set of user-generated reviews includes a user-generated review for a first entity and a user-generated review for a second entity. The first entity is different from the second entity. The method includes providing at least a portion of the user-generated review for the first entity and at least a portion of the user-generated review for the second entity for simultaneous display on a comparison layout of a user interface of the client device.

PRIVACY-SENSITIVE TRAINING OF USER INTERACTION PREDICTION MODELS (18350860)

Main Inventor

Lukas Zilka

Brief explanation

- This patent application describes methods, systems, and apparatus for collaboratively training an interaction prediction machine learning model.

- The goal is to train the model using multiple user devices while respecting user privacy. - The machine learning model processes a search query and a data element as input. - It generates an output that represents the likelihood of a user interacting with the data element if it were presented on a webpage. - The model uses search results that are responsive to the search query to make predictions. - The innovation focuses on privacy by ensuring that user data is protected during the collaborative training process. - The patent application emphasizes the use of computer programs encoded on a computer storage medium to implement the methods and systems described. - The abstract provides a high-level overview of the patent application, highlighting the key aspects and objectives of the innovation.

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for collaboratively training an interaction prediction machine learning model using a plurality of user devices in a manner that respects user privacy. In one aspect, the machine learning model is configured to process an input comprising: (i) a search query, and (ii) a data element, to generate an output which characterizes a likelihood that a given user would interact with the data element if the data element were presented to the given user on a webpage identified by a search result responsive to the search query.

DATA INTEGRITY (18330596)

Main Inventor

Arthur Weinberger

Brief explanation

The patent application describes methods, systems, and apparatus for protecting analytics for a publisher's resources from malicious traffic. 

• The analytics server receives a message containing encrypted token and analytics data for a publisher-provided resource.
• The token includes a portion of the analytics data and a trust score indicating the likelihood of human activity on the resource.
• The analytics server decrypts the token and determines a trustworthiness measure for the analytics data.
• The trustworthiness measure is based on the trust score and a comparison of the analytics data in the message and the portion in the token.
• Based on the measure of trustworthiness, the analytics server performs analytics operations using the analytics data.

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, that protect analytics for resources of a publisher from traffic directed to such resources by malicious entities. An analytics server receives a first message that includes an encrypted token and analytics data for a publisher-provided resource. The token includes a portion of the analytics data and a trust score indicating a likelihood that activity on the resource is attributed to a human (rather than an automated process). The analytics server decrypts the token. The analytics server determines a trustworthiness measure for the analytics data included in the first message based on the trust score (in the decrypted token) and a comparison of the analytics data in the first message and the portion of the analytics data (in the decrypted token). Based on the measure of trustworthiness, the analytics server performs analytics operations using the analytics data.

Modeling Ambiguity in Neural Machine Translation (18089684)

Main Inventor

Felix Stahlberg

Brief explanation

The technology aims to improve neural machine translation by addressing ambiguity.

• An encoder module generates an encoded representation of a given text exemplar.
• A decoder module receives the encoded representation and a set of translation prefixes.
• The decoder module outputs a set of tokens associated with each pair of the exemplar and translation prefix.
• Each token is assigned a probability in the exemplar's vocabulary at each time step.
• A logits module generates bounded conditional probabilities for each token based on the unbounded function.
• The probabilities are not normalized over the vocabulary at each time step.
• A loss function module identifies whether each target text is a valid translation of the exemplar.
• The loss function module has a positive loss component and a scaled negative loss component.

Abstract

The technology addresses ambiguity in neural machine translation. An encoder module receives a given text exemplar and generates an encoded representation of it. A decoder module receives the encoded representation and a set of translation prefixes. The decoder module outputs an unbounded function corresponding to a set of tokens associated with each pair of the given text exemplar and translation prefix from the set of translation prefixes. Each token is assigned a probability between 0 and 1 in a vocabulary of the exemplar at each time step. A logits module generates, based on the unbounded function, a corresponding bounded conditional probability for each token, wherein the probabilities are not normalized over the vocabulary at each time step. A loss function module having a positive loss component and a scaled negative loss component identifies whether each target text of a set of target texts is a valid translation of the exemplar.

CONTRASTIVE CAPTIONING NEURAL NETWORKS (18141340)

Main Inventor

Jiahui Yu

Brief explanation

- This patent application is about methods, systems, and apparatus for processing multi-modal inputs using contrastive captioning neural networks.

- The invention involves computer programs encoded on computer storage media. - The purpose is to improve the processing of multi-modal inputs, which are inputs that involve multiple modes of communication such as text, images, and audio. - The invention utilizes contrastive captioning neural networks, which are a type of artificial intelligence model that can generate captions for images or other visual inputs. - The patent application covers various aspects of the invention, including the methods, systems, and apparatus used in the processing of multi-modal inputs. - The invention may have applications in fields such as computer vision, natural language processing, and multimedia analysis. - The patent application does not provide a specific title for the invention.

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing multi-modal inputs using contrastive captioning neural networks.

NEURAL NETWORKS WITH SWITCH LAYERS (18349089)

Main Inventor

William Bradley Fedus

Brief explanation

The patent application describes methods, systems, and apparatus for using machine learning to process network inputs and generate network outputs. 

• The invention involves a neural network that is designed to perform the machine learning task.
• The neural network includes one or more switch layers, which are specific layers within the network architecture.
• The purpose of these switch layers is not explicitly mentioned in the abstract, but they likely serve a specific function in enhancing the machine learning capabilities of the network.
• The patent application also mentions computer programs encoded on a computer storage medium, indicating that the invention may involve software implementation.
• The abstract does not provide specific details about the machine learning task or the type of network input and output, leaving those aspects open to interpretation.

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input to generate a network output. In one aspect, one of the systems includes a neural network configured to perform the machine learning task, the neural network including one or more switch layers.

DETERMINISTIC TRAINING OF MACHINE LEARNING MODELS (18219555)

Main Inventor

Gaurav Mishra

Brief explanation

The patent application describes a method for training a machine learning model using a deterministic data pipeline. Here are the key points:

• The method involves generating a deterministic training dataset by transforming raw training examples obtained from a raw data source into pre-processed training examples.
• Each pre-processed training example is assigned a unique index.
• The pre-processed training examples are cached into a specified cache directory.
• The method also involves using the deterministic training dataset to train a machine learning model.
• A second request is received, specifying a start index for reading the pre-processed training examples from the cache directory.
• The pre-processed training examples with indices beginning from the start index are read from the cache directory.
• The read training examples are provided in the order of the assigned indices for use in training the machine learning model.

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a machine learning model using a deterministic data pipeline. One of the methods may include receiving a first request to generate a deterministic training dataset: transforming raw training examples obtained from the raw data source into pre-processed training examples; assigning a unique index to each pre-processed training example; and caching the pre-processed training examples into the cache directory specified in the received first request; receiving a second request to use the deterministic training dataset to train a machine learning model, the second request specifying a start index; and in response to receiving the second request: reading, from the cache directory, the pre-processed training examples that have indices beginning from the start index; and providing the read training examples in an order of the assigned indices for use in training the machine learning model.

ROBUST TRAINING IN THE PRESENCE OF LABEL NOISE (18348587)

Main Inventor

Zizhao Zhang

Brief explanation

The patent application describes a method for training a model using labeled training samples. 

• Obtaining a set of labeled training samples with given labels
• Generating pseudo labels and estimating the accuracy of the given labels
• Determining if the weight of a labeled training sample meets a threshold
• Adding the sample to a set of cleanly labeled samples if the weight threshold is met
• Adding the sample to a set of mislabeled samples if the weight threshold is not met
• Training the model using the cleanly labeled samples with given labels
• Training the model using the mislabeled samples with corresponding pseudo labels

Abstract

A method for training a model comprises obtaining a set of labeled training samples each associated with a given label. For each labeled training sample, the method includes generating a pseudo label and estimating a weight of the labeled training sample indicative of an accuracy of the given label. The method also includes determining whether the weight of the labeled training sample satisfies a weight threshold. When the weight of the labeled training sample satisfies the weight threshold, the method includes adding the labeled training sample to a set of cleanly labeled training samples. Otherwise, the method includes adding the labeled training sample to a set of mislabeled training samples. The method includes training the model with the set of cleanly labeled training samples using corresponding given labels and the set of mislabeled training samples using corresponding pseudo labels.

UTILIZING ELASTIC WEIGHT CONSOLIDATION (EWC) LOSS TERM(S) TO MITIGATE CATASTROPHIC FORGETTING IN FEDERATED LEARNING OF MACHINE LEARNING MODEL(S) (17734766)

Main Inventor

Andrew Hard

Brief explanation

This patent application is about using elastic weight consolidation (EWC) loss term(s) in federated learning of global machine learning (ML) models. Here are the key points:

• The technology focuses on utilizing EWC loss term(s) in federated learning.
• A global ML model is initially trained on a remote server using a server data set.
• EWC loss term(s) for the global weights of the ML model are determined based on a Fisher information matrix for the server data set.
• The global ML model and the EWC loss term(s) are transmitted to multiple client devices.
• The client devices generate client gradients based on processing predicted output using the global ML model and the EWC loss term(s).
• The client gradients are then transmitted back to the remote server.
• An updated global ML model is generated based on the client gradients received from the client devices.

Abstract

Implementations disclosed herein are directed to utilizing elastic weight consolidation (EWC) loss term(s) in federated learning of global machine learning (ML) models. Implementations may identify a global ML model that initially trained at a remote server based on a server data set, determine the EWC loss term(s) for global weight(s) of the global ML model, and transmit the global ML model and the EWC loss term(s) to a plurality of client devices. The EWC loss term(s) may be determined based on a Fisher information matrix for the server data set. Further, the plurality client devices may generate, based on processing corresponding predicted output and using the global ML model, and based on the EWC loss term(s), a corresponding client gradient, and transmit the corresponding client gradient to the remote server. Implementations may further generate an updated global ML model based on at least the corresponding client gradients.

CUSTOMIZED PREDICTIVE ANALYTICAL MODEL TRAINING (18348217)

Main Inventor

Jordan M. Breckenridge

Brief explanation

The patent application describes methods, systems, and apparatus for training predictive models using multiple training data records.

• The training data records consist of an input data portion and an output data portion.
• The training data type is determined by inputting the output data portions into trained predictive classifiers or comparing them to data formats.
• Based on the determined training data type, a set of training functions compatible with the training data are identified.
• The identified set of training functions and the training data are used to train multiple predictive models.

Abstract

Methods, systems, and apparatus, including computer programs encoded on one or more computer storage devices, for training predictive models. Multiple training data records are received that each include an input data portion and an output data portion. A training data type is determined that corresponds to the training data. For example, a training data type can be determined by inputting the output data portions into one or more trained predictive classifiers. In other example, the training data type can be determined by comparison of the output data portions to data formats. Based on the determined training data type, a set of training functions are identified that are compatible with the training data of the determined training data type. The training data and the identified set of training functions are used to train multiple predictive models.

Systems and Methods for Annotating Online Content with Offline Interaction Data (18344966)

Main Inventor

Vinod Kumar Ramachandran

Brief explanation

The abstract describes a computer-implemented method for annotating online content with offline interaction data and offline interaction conversion data.

• The method involves a content annotating computing device in communication with a memory.
• It starts by receiving content interaction data from an online user's interaction with a first online content item.
• It then identifies physical locations associated with the online content provider.
• Based on the content interaction data and offline interaction data, a set of offline interaction conversion data is determined.
• Next, a second online content item associated with the online content provider is received.
• The second online content item is annotated using the offline interaction conversion data and offline interaction data.

Abstract

A computer-implemented method for annotating online content with offline interaction data and offline interaction conversion data is implemented by a content annotating computing device in communication with a memory. The method includes receiving a set of content interaction data based on an online interaction between an online user and a first online content item, identifying at least one physical location associated with the online content provider, determining a set of offline interaction conversion data based on the set of content interaction data and a set of offline interaction data, receiving a second online content item associated with the online content provider, and annotating the second online content item based at least partially on the set of offline interaction conversion data and the set of offline interaction data.

Systems and Methods for Manipulation of Shadows on Portrait Image Frames (17786841)

Main Inventor

David Jacobs

Brief explanation

- The patent application describes a method for training a machine learning model to be used on a mobile device for capturing and adjusting image frames.

- The method involves supplying two image frames of a subject in different lighting environments and determining a mask. - The first and second image frames are then combined using the mask to generate a synthetic image. - A score is assigned to the synthetic image, and a machine learning model is trained based on this score. - The trained model can then be used to adjust captured images based on the synthetic image, improving the quality of the final image.

Abstract

Systems and methods described herein may relate to potential methods of training a machine learning model to be implemented on a mobile computing device configured to capture, adjust, and/or store image frames. An example method includes supplying a first image frame of a subject in a setting lit within a first lighting environment and supplying a second image frame of the subject lit within a second lighting environment. The method further includes determining a mask. Additionally, the method includes combining the first image frame and the second image frame according to the mask to generate a synthetic image and assigning a score to the synthetic image. The method also includes training a machine learning model based on the assigned score to adjust a captured image based on the synthetic image.

Systems and Methods for Object Detection Including Pose and Size Estimation (17800688)

Main Inventor

Tingbo Hou

Brief explanation

The patent application is about systems and methods for detecting objects and estimating their position and size in 3D based on 2D images.

• Object detection is done using a machine-learned model that can determine different properties of objects.
• The properties of the objects are then used to estimate their pose (position and orientation) and size.
• This technology can be used to accurately detect and measure objects in 3D using only 2D images.
• The system is designed to improve object detection and pose estimation in various applications.
• The method can be implemented using computer vision algorithms and machine learning techniques.
• The innovation has potential applications in fields such as robotics, augmented reality, and autonomous vehicles.

Abstract

The present disclosure is directed to systems and methods for performing object detection and pose estimation in 3D from 2D images. Object detection can be performed by a machine-learned model configured to determine various object properties. Implementations according to the disclosure can use these properties to estimate object pose and size.

Compensating for Non-Uniform Luminance in Curved-Edge Displays (18126874)

Main Inventor

Chien-Hui Wen

Brief explanation

This patent application describes a system and method for compensating for non-uniform luminance in curved-edge displays. 

• A computing device with a curved-edge display and a luminance manager receives information about the luminance displayed by the pixels on the curved-edge display.
• The luminance manager analyzes the received luminance information and the non-uniform luminance of the display.
• Based on this analysis, the luminance manager determines how to modify the luminance of the pixels on the curved-edge display.
• The determined luminance modification is then applied to either the displayed luminance or the intended luminance to compensate for the non-uniform luminance.
• This system and method help ensure a more uniform and consistent luminance across the entire curved-edge display.

Abstract

This document describes systems and techniques directed at compensating for non-uniform luminance in curved-edge displays. In aspects, a computing device having a curved-edge display and a luminance manager is configured to receive an indication of a luminance that is, or is intended to be, displayed by pixels of the curved-edge display. Responsive to and based on the received indication of the luminance and a non-uniform luminance, the luminance manager determines a luminance modification for the pixels of the curved-edge display. Based on the determined luminance modification, the luminance manager modifies the luminance that is displayed or modifies the intended luminance that is intended to be displayed by pixels of the curved-edge display effective to compensate for the non-uniform luminance.

MIXED CLIENT-SERVER FEDERATED LEARNING OF MACHINE LEARNING MODEL(S) (18218319)

Main Inventor

Françoise Beaufays

Brief explanation

This patent application is about a method for federated learning of machine learning models using gradients generated on client devices and a remote system. 

• The method involves client devices processing local data using on-device ML models to generate predicted outputs and gradients.
• The client devices then transmit these gradients to a remote system.
• The remote system processes remote data from databases using global ML models to generate additional predicted outputs and gradients.
• The client gradients and remote gradients are used to update the global ML models or their weights.
• The updated global ML models or weights are then sent back to the client devices.

Abstract

Implementations disclosed herein are directed to federated learning of machine learning (“ML”) model(s) based on gradient(s) generated at corresponding client devices and a remote system. Processor(s) of the corresponding client devices can process client data generated locally at the corresponding client devices using corresponding on-device ML model(s) to generate corresponding predicted outputs, generate corresponding client gradients based on the corresponding predicted outputs, and transmit the corresponding client gradients to the remote system. Processor(s) of the remote system can process remote data obtained from remote database(s) using global ML model(s) to generate additional corresponding predicted outputs, generate corresponding remote gradients based on the additional corresponding predicted outputs. Further, the remote system can utilize the corresponding client gradients and the corresponding remote gradients to update the global ML model(s) or weights thereof. The updated global ML model(s) and/or the updated weights thereof can be transmitted back to the corresponding client devices.

TIED AND REDUCED RNN-T (18347842)

Main Inventor

Rami Botros

Brief explanation

The abstract describes a Recurrent Neural Network Transducer (RNN-T) model used for speech recognition. Here are the key points:

• The RNN-T model includes a prediction network and a joint network.
• The prediction network receives a sequence of non-blank symbols at each time step.
• It generates an embedding for each non-blank symbol using a shared embedding matrix.
• It assigns a position vector to each non-blank symbol and weights the embedding based on similarity to the position vector.
• The prediction network generates a single embedding vector at each time step.
• The joint network receives the embedding vector from the prediction network and generates a probability distribution over possible speech recognition hypotheses.
• The RNN-T model is designed to improve speech recognition accuracy and efficiency.

Abstract

A RNN-T model includes a prediction network configured to, at each of a plurality of times steps subsequent to an initial time step, receive a sequence of non-blank symbols. For each non-blank symbol the prediction network is also configured to generate, using a shared embedding matrix, an embedding of the corresponding non-blank symbol, assign a respective position vector to the corresponding non-blank symbol, and weight the embedding proportional to a similarity between the embedding and the respective position vector. The prediction network is also configured to generate a single embedding vector at the corresponding time step. The RNN-T model also includes a joint network configured to, at each of the plurality of time steps subsequent to the initial time step, receive the single embedding vector generated as output from the prediction network at the corresponding time step and generate a probability distribution over possible speech recognition hypotheses.

CROSS-DEVICE DATA SYNCHRONIZATION BASED ON SIMULTANEOUS HOTWORD TRIGGERS (18221274)

Main Inventor

Matthew Sharifi

Brief explanation

This patent application describes techniques for synchronizing data between multiple devices using hotword triggers. Here is a simplified explanation of the abstract:

• The patent application describes a method for synchronizing data between devices using an automated assistant.
• The method involves executing the automated assistant on a first device in an inactive state.
• While in the inactive state, the assistant listens to audio data captured by the device's microphones.
• The audio data is processed using a machine learning model to determine if it contains specific hotwords.
• If the hotwords are detected, arbitration is performed with other devices running the assistant.
• Once arbitration is completed, synchronization of user data or configuration data is initiated between the devices.
• The user data includes information based on interactions with the user on the first device prior to the audio data being received.

Abstract

Techniques are described herein for cross-device data synchronization based on simultaneous hotword triggers. A method includes: executing a first instance of an automated assistant in an inactive state at least in part on a first computing device operated by a user; while in the inactive state, receiving, via one or more microphones of the first computing device, audio data that captures a spoken utterance of the user; processing the audio data using a machine learning model to generate a predicted output that indicates a probability of one or more hotwords being present in the audio data; determining that the predicted output satisfies a threshold that is indicative of the one or more hotwords being present in the audio data; in response to determining that the predicted output satisfies the threshold, performing arbitration with at least one other computing device that is executing at least in part at least one other instance of the automated assistant; and in response to performing arbitration with the at least one other computing device, initiating synchronization of user data or configuration data between the first instance of the automated assistant on the first computing device and the at least one other instance of the automated assistant on the at least one other computing device, the user data comprising data that is based on one or more interactions with the user at the first computing device, the one or more interactions occurring prior to the receiving of the audio data.

PLATFORM SELECTION FOR PERFORMING REQUESTED ACTIONS IN AUDIO-BASED COMPUTING ENVIRONMENTS (18217938)

Main Inventor

Chad Ward

Brief explanation

The patent application describes a system and method for selecting digital platforms to execute voice-based commands.

• The system receives an application that performs an action associated with a service via digital platforms.
• The system debugs the application to validate parameters of the action on at least two platforms.
• The system receives data packets containing an input audio signal from a client device's sensor.
• The input audio signal is parsed to identify the action and the service.
• A first platform is selected from the digital platforms to perform the action.
• An interactive data exchange is initiated to populate parameters of an action data structure corresponding to the action.
• The action is executed via the selected platform using the action data structure.

Abstract

Systems and methods of selecting digital platforms for execution of voice-based commands are provided. The system receives an application that performs an action associated with a service via digital platforms. The system debugs the application to validate parameters of the action on at least two platforms of the digital platforms. The system receives data packets comprising an input audio signal detected by a sensor of a client device, and parses the input audio signal to identify the action and the service. The system selects a first platform from the digital platforms to perform the action. The system initiates, responsive to selection of the first platform, an interactive data exchange to populate parameters of an action data structure corresponding to the action. The system executes the action via the selected platform using the action data structure.

RECOMMENDING AUTOMATED ASSISTANT ACTION FOR INCLUSION IN AUTOMATED ASSISTANT ROUTINE (18218333)

Main Inventor

Michael Andrew Goodman

Brief explanation

The patent application describes a method for recommending and adding new actions to an existing automated assistant routine.

• The existing routine already has multiple preexisting actions.
• The user is presented with a recommendation for a new action to be added to the routine.
• If the user confirms the recommendation, the new action is automatically added to the routine.
• When the routine is initialized, both the preexisting actions and the newly added action will be performed.

Abstract

Recommending an automated assistant action for inclusion in an existing automated assistant routine of a user, where the existing automated assistant routine includes a plurality of preexisting automated assistant actions. If the user confirms the recommendation through affirmative user interface input, the automated assistant action can be automatically added to the existing automated assistant routine. Thereafter, when the automated assistant routine is initialized, the preexisting automated assistant actions of the routine will be performed, as well as the automated assistant action that was automatically added to the routine in response to affirmative user interface input received in response to the recommendation.

USING CORRECTIONS, OF AUTOMATED ASSISTANT FUNCTIONS, FOR TRAINING OF ON-DEVICE MACHINE LEARNING MODELS (18218818)

Main Inventor

Françoise Beaufays

Brief explanation

The patent application describes a system where a client device can use sensor data and machine learning to activate automated assistant functions. If the device makes an incorrect decision, it can generate a gradient to update the on-device speech recognition model. The gradient can also be sent to a remote system to update a global speech recognition model.

• Client devices can use sensor data and machine learning to activate automated assistant functions.
• If the device makes an incorrect decision, it can generate a gradient based on the predicted output compared to the ground truth output.
• The generated gradient can be used to update the on-device speech recognition model.
• The gradient can also be sent to a remote system to update a global speech recognition model.

Abstract

Processor(s) of a client device can: receive sensor data that captures environmental attributes of an environment of the client device; process the sensor data using a machine learning model to generate a predicted output that dictates whether one or more currently dormant automated assistant functions are activated; making a decision as to whether to trigger the one or more currently dormant automated assistant functions; subsequent to making the decision, determining that the decision was incorrect; and in response to determining that the determination was incorrect, generating a gradient based on comparing the predicted output to ground truth output. In some implementations, the generated gradient is used, by processor(s) of the client device, to update weights of the on-device speech recognition model. In some implementations, the generated gradient is additionally or alternatively transmitted to a remote system for use in remote updating of global weights of a global speech recognition model.

VOICE COMMANDS ACROSS DEVICES (18348152)

Main Inventor

Jennifer Shien-Ming Chen

Brief explanation

The patent application describes a method for using voice commands on multiple computing devices.

• Voice input data is received from a first computing device and a second computing device associated with a user account.
• An intended voice command is determined based on the obtained voice input data.
• A target computing device is determined based on the intended voice command.
• Instructions associated with the intended voice command are provided to the target computing device for execution.

Abstract

Aspects of the subject technology relate to a method for using a voice command for multiple computing devices. First voice input data is received from a first computing device associated with a user account, where the first voice input data comprises a first voice command captured at the first computing device. Second voice input data is received from a second computing device associated with the user account where the second voice input data comprises a second voice command captured at the second computing device. An intended voice command is determined based on the obtained first and second voice input data. Based on the intended voice command, a first target computing device is determined. First instructions associated with the intended voice command are provided to the first target computing device for execution.

AUTOMATED CALLING SYSTEM (18219480)

Main Inventor

Asaf Aharoni

Brief explanation

The patent application describes an automated calling system that uses speech recognition and synthesis technology to generate replies in a telephone conversation between a user and a bot. 

• The system receives audio data of the user's utterance during the conversation.
• It determines the context of the conversation to understand the current topic or subject.
• The system also analyzes the user's intent in the previous part of the conversation and the bot's intent in its previous response.
• Using the audio data, context, user intent, and bot intent, the system generates a synthesized speech reply from the bot.
• The synthesized speech is then provided as the output of the system.

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for an automated calling system are disclosed. In one aspect, a method includes the actions of receiving audio data of an utterance spoken by a user who is having a telephone conversation with a bot. The actions further include determining a context of the telephone conversation. The actions further include determining a user intent of a first previous portion of the telephone conversation spoken by the user and a bot intent of a second previous portion of the telephone conversation outputted by a speech synthesizer of the bot. The actions further include, based on the audio data of the utterance, the context of the telephone conversation, the user intent, and the bot intent, generating synthesized speech of a reply by the bot to the utterance. The actions further include, providing, for output, the synthesized speech.

TRAINED GENERATIVE MODEL SPEECH CODING (17757122)

Main Inventor

Willem Bastiaan Kleijn

Brief explanation

- The patent application describes a method for training a machine learning model to generate high-quality audio from a low bitrate input.

- The method involves receiving sampled audio data of utterances and using it to train the machine learning model. - The training process includes reducing the impact of low-probability distortion events in the audio data on the trained model. - This is achieved by including a term in the objective function of the model that encourages low-variance predictive distributions of the next audio sample based on previous samples. - The goal is to improve the fidelity of the generated audio stream while using a low bitrate input.

Abstract

A method includes receiving sampled audio data corresponding to utterances and training a machine learning (ML) model, using the sampled audio data, to generate a high-fidelity audio stream from a low bitrate input bitstream. The training of the ML model includes de-emphasizing the influence of low-probability distortion events in the sampled audio data on the trained ML model, where the de-emphasizing of the distortion events is achieved by the inclusion of a term in an objective function of the ML model, which term encourages low-variance predictive distributions of a next sample in the sampled audio data, based on previous samples of the audio data.

CONTROL AND/OR REGISTRATION OF SMART DEVICES, LOCALLY BY AN ASSISTANT CLIENT DEVICE (18349660)

Main Inventor

Vincent Mo

Brief explanation

The patent application relates to generating control commands on an assistant client device that can be directly interpreted by a smart device to change its state or control another smart device.

• The innovation allows for specific control commands to be generated on an assistant client device.
• These commands can be transmitted to a smart device and directly interpreted by the smart device.
• The smart device can then use these commands to change its own state or control another smart device.
• The assistant client device can be used to discover, provision, and register smart devices for a user's account.

Abstract

Various implementations relate to generating, locally at an assistant client device, specific control commands that, when transmitted to a corresponding smart device, are directly interpretable by the corresponding smart device to effectuate a state change at the corresponding smart device, or at a corresponding additional smart device directly controlled by the corresponding smart device. Various implementations additionally or alternatively relate to utilizing local assistant client devices in discovering, provisioning, and/or registering smart devices for an account of a user.

METHODS, SYSTEMS, AND MEDIA FOR DETECTING THE PRESENCE OF A DIGITAL MEDIA DEVICE ON A NETWORK (18219995)

Main Inventor

Ant Oztaskent

Brief explanation

The abstract describes methods, systems, and media for detecting the presence of a digital media device on a network. 

• The methods involve identifying cached device details for previously associated devices on the network.
• A simple device discovery protocol (SSDP) is performed on the network, along with sending a unicast message to an address associated with the identified cached digital media device using hypertext transfer protocol (HTTP).
• The presence of a digital media device on the network is indicated if a response is received to the unicast message or if the device discovered using SSDP is of the same type as the particular device being detected.

Abstract

Methods, systems, and media for detecting the presence of a digital media device on a network are provided. In some embodiments, methods for detecting a presence of a particular type of digital media device is provided, the methods comprising: identifying cached device details for devices previously associated with the network; performing a simple device discovery protocol (SSDP) on the network, and substantially concurrently sending a unicast message to an address associated with the identified cached digital media device using hypertext transfer protocol (HTTP); and indicating the presence of a digital media device on the network in response to either (i) receiving a response to the unicast message, or (ii) determining that a type of a device discovered using SSDP is the same as the particular device type.

DETERMINING REPLY CONTENT FOR A REPLY TO AN ELECTRONIC COMMUNICATION (18070231)

Main Inventor

Phillip Neal Sharp

Brief explanation

The patent application is about methods and apparatus for determining reply content for electronic communications.

• The application focuses on analyzing a collection of electronic communications to understand the relationship between the original message features and the reply content.
• It also aims to provide reply text suggestions based on the message features of the communication and the determined relationships.

Abstract

Methods and apparatus related to determining reply content for a reply to an electronic communication. Some implementations are directed generally toward analyzing a corpus of electronic communications to determine relationships between one or more original message features of “original” messages of electronic communications and reply content that is included in “reply” messages of those electronic communications. Some implementations are directed generally toward providing reply text to include in a reply to a communication based on determined relationships between one or more message features of the communication and the reply text.

SYSTEMS AND METHODS FOR DISPLAYING UNSEEN LABELS IN A CLUSTERING IN-BOX ENVIRONMENT (18337158)

Main Inventor

Itamar Gilad

Brief explanation

The patent application describes a method for displaying electronic messages on a computing device.

• The method involves receiving multiple electronic messages.
• The messages are then categorized into predefined groups based on their content using clustering rules.
• A subset of the messages and a cluster graphic representing the group category are displayed together.
• The user can select the cluster graphic to view all the messages in that group.
• This allows for easy organization and navigation of messages based on their content.

Abstract

Systems and methods for displaying electronic messages are disclosed. In one aspect, a method is performed at a computing device. The method includes: (1) receiving a plurality of electronic messages; (2) assigning a first subset of the messages to a predefined group category based on a set of content-based clustering rules and content in respective bodies of the messages; (3) concurrently displaying a second subset of the messages and a cluster graphic corresponding to the predefined group category, where the cluster graphic includes a label that describes the predefined group category; (4) while concurrently displaying the second subset of electronic messages and the cluster graphic, receiving user selection of the cluster graphic; and (5) in response, displaying a plurality of messages in the predefined group category, including displaying at least one message from the first subset of messages.

Hybrid Content Protection Architecture for Email (18350451)

Main Inventor

Nicolas Lidzborski

Brief explanation

The abstract describes a computer-implemented method that allows a user device to obtain and decrypt an encrypted message using a single-use data encryption key (DEK).

• Obtains an encrypted message and an encrypted DEK from a message server.
• Transmits a decryption request to a key access control list server (KACLS) to decrypt the encrypted DEK.
• The KACLS is separate from the message server.
• Receives the decrypted single-use DEK from the KACLS.
• Decrypts the encrypted message using the single-use DEK.

Abstract

A computer-implemented method when executed by data processing hardware of a user device causes the data processing hardware to perform operations. The operations include obtaining, from a message server, an encrypted message encrypted by a single-use data encryption key (DEK) and an encrypted DEK including the single-use DEK encrypted by a public key (PK). The operations also include transmitting, to a key access control list server (KACLS), a decryption request requesting the KACLS decrypt the encrypted DEK with a PRK associated with the PK. The decryption request includes the encrypted DEK. The KACLS is independent from the message server. The operations also include receiving, from the KACLS, the single-use DEK and decrypting, using the single-use DEK, the encrypted message.

INDICATING CALLERS FOR INCOMING VOICE CALLS ON A SHARED SPEECH-ENABLED DEVICE (18220068)

Main Inventor

Ahmet Onur Tekdas

Brief explanation

The patent application is about a method, system, and apparatus for indicating callers for incoming voice calls.

• The invention involves receiving an incoming voice call and determining the calling number and called number.
• It then identifies a user account that corresponds to the called number.
• The system determines a contact name for the calling number based on contact entries for the user account.
• Finally, it provides the contact name for output, allowing the user to see who is calling.

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for indicating callers for incoming voice calls. The methods, systems, and apparatus include actions receiving an incoming voice call, determining a calling number and a called number from the incoming voice call, identifying a user account that corresponds to the called number, determining a contact name for the calling number based on contact entries for the user account, and providing the contact name for output.

ENCODING AND DECODING USING TILING (18342024)

Main Inventor

Ronald Sebastiaan Bultje

Brief explanation

- The patent application is about video coding using tiling.

- Tiling is used to encode a current frame by dividing it into smaller tiles. - Each tile has a tile-width and tile-height, indicating the number of horizontally and vertically adjacent blocks within the tile. - The current tile is encoded by generating an encoded tile, where each row of the tile includes horizontally adjacent blocks and each column includes vertically adjacent blocks. - The encoded tile is outputted, and its size is included in the output bitstream to indicate the number of bytes needed to include the encoded tile.

Abstract

Video coding using tiling may include encoding a current frame by identifying a tile-width for encoding a current tile of the current frame, the tile-width indicating a cardinality of horizontally adjacent blocks in the current tile, identifying a tile-height for encoding the current tile of the current frame, the tile-height indicating a cardinality of vertically adjacent block in the current tile, and generating an encoded tile by encoding the current tile, such that a row of the current tile includes tile-width horizontally adjacent blocks from the plurality of blocks, and a column of the current tile includes tile-height vertically adjacent blocks from the plurality of blocks. Encoding the current frame may include outputting the encoded tile, wherein outputting the encoded tile includes including an encoded-tile size in an output bitstream, the encoded-tile size indicating a cardinality of bytes for including the encoded tile in the output bitstream.

METHODS, SYSTEMS, AND MEDIA FOR PRESENTING MEDIA CONTENT ITEMS USING MULTIPLE DEVICES (18219883)

Main Inventor

Tom Jaspers

Brief explanation

This patent application describes mechanisms for presenting media content items using multiple devices. Here are the key points:

• The invention allows for presenting media content on a media device that has not been authenticated with a content service.
• When an offer to purchase a content item is detected, the media device becomes discoverable by mobile devices on the same local area network.
• The offer data associated with the purchase is encoded and transmitted to a mobile device, which then presents a payment user interface.
• Once the purchase is initiated, the mobile device can request to cast the content item on the media device.
• In response to the cast request, a receiver application on the media device accepts the request and presents the content item.

Abstract

Mechanisms for presenting media content items using multiple devices are provided. In some embodiments, methods for presenting media content are provided that include: detecting an offer to initiate a purchase of a content item being presented using the media device, wherein the media device has not been authenticated with a content service that provides the content item; in response to detecting the offer to initiate the purchase of the content item when the media device has not been authenticated with the content service that provides the content item, causing the media device to be discoverable by one or more mobile devices that are connected to a same local area network as the media device; encoding offer data corresponding to the detected offer to initiate the purchase of the content item; in response to receiving a status request from a mobile device that is connected to the same local area network as the media device, transmitting the encoded offer data associated with the purchase of the content item to the mobile device, wherein the encoded offer data causes a payment user interface to be presented on the mobile device; receiving a cast request from the mobile device to cast the content item on the media device; and in response to the cast request, executing a receiver application on the media device that accepts the cast request from the mobile device and causes the content item to be presented using the media device.

Systems and Methods for Improved Searching and Categorizing of Media Content Items Based on a Destination for the Media Content Machine Learning (18349533)

Main Inventor

David McIntosh

Brief explanation

The patent application describes a computer-implemented method for selecting and displaying media content items based on the destination of the content.

• The method involves receiving data that describes the destination of the media content item, such as the recipient of a message or a digital location.
• Based on this data, the computing system selects one or more media content items that are relevant and appropriate for the destination.
• The selected media content items are then displayed in a dynamic keyboard interface on the user's computing device.
• This technology aims to provide users with more relevant and suitable media content options based on where the content is intended to be shared or displayed.

Abstract

Aspects of the present disclosure are directed to a computer-implemented method including receiving, by a user computing device, data that describes a destination for the media content item. Example destinations can include a location of a recipient of message including the media content item and a digital location (e.g., website, social networking page, etc.). The method can include selecting, by a computing system comprising the user computing device, one or more media content items based on the data that describes the destination for the media content item. Media content items that are more relevant and/or appropriate can be selected by considering the destination of the media content item. The selected media content item(s) can be provided for display by the user computing device in a dynamic keyboard interface.

INTEGRATING SHORT-TERM CONTEXT FOR CONTENT PLAYBACK ADAPTION (18349658)

Main Inventor

Victor Carbune

Brief explanation

- The patent application describes a method for an assistant-enabled device to adjust content playback settings based on contextual signals from its environment.

- The device receives a contextual signal and uses an event recognition routine to determine if the signal indicates an event that conflicts with the media content being played. - If a conflict is detected, the device adjusts the content playback settings accordingly. - The purpose of this innovation is to ensure that the assistant-enabled device can adapt its playback settings to accommodate any events in the environment that may interfere with the media content being played.

Abstract

While an assistant-enabled device is playing back media content, a method includes receiving a contextual signal from an environment of the assistant-enabled device and executing an event recognition routine to determine whether the received contextual signal is indicative of an event that conflicts with the playback of the media content from the assistant-enabled device. When the event recognition routine determines that the received contextual signal is indicative of the event that conflicts with the playback of the media content, the method also includes adjusting content playback settings of the assistant-enabled device.

AUDIO PANEL TEMPERATURE CONTROL (17639371)

Main Inventor

Jennis Jose

Brief explanation

- The patent application describes a mobile device with a panel audio loudspeaker that includes a display panel and an actuator.

- The mobile device also includes a temperature sensor that detects the temperature of the display panel. - An electronic control module is programmed to adjust the power signal provided to the actuator based on the temperature data from the sensor. - The power signal is adjusted by selecting a target temperature for the display panel based on the temperature data. - The target temperature is then mapped to a target power level, and the power signal provided to the actuator is changed to match the target power level.

Abstract

A mobile device includes a panel audio loudspeaker including a display panel and an actuator coupled to the display panel. The mobile device includes a temperature sensor arranged to sense a temperature of the display panel, and an electronic control module in communication with the actuator and the temperature sensor. The electronic control module is programmed to perform operations including: obtaining, from the temperature sensor, data indicating a temperature of the display panel; and based on the data indicating the temperature of the display panel, adjusting a power signal provided to the actuator to drive the panel audio loudspeaker. The power signal can be adjusted by selecting, based on the data indicating the temperature of the display panel, a target temperature of the display panel; mapping the target temperature to a target power level; and changing the power signal provided to the actuator to the target power level.

Securing Return Communication Through Application Uniform Resource Locators (18306870)

Main Inventor

Tennessee Carmel-Veilleux

Brief explanation

- This patent application describes techniques and devices for securing return communication through application uniform resource locators (URLs).

- The purpose of these techniques and devices is to commission a joiner device to a home area network by an initiator device. - The initiator device obtains a Responder Access URL and uses it to generate an Augmented Responder Access URL. - The initiator device then accesses the Augmented Responder Access URL at a responder, which triggers the generation of a Responder Payload. - The initiator device accesses an Augmented Initiator Response URL that includes the generated Responder Payload. - By recovering the Responder Payload, the initiator device is able to commission the joiner device to the home area network.

Abstract

Techniques and devices for securing return communication through application uniform resource locators are described for commissioning a joiner device to a home area network by an initiator device in which the initiator device obtains a Responder Access Uniform Resource Locator (URL) and using the obtained Responder Access URL, generates an Augmented Responder Access URL. The initiator device accesses the Augmented Responder Access URL at a responder, which causes the responder to generate a Responder Payload. The initiator device accesses an Augmented Initiator Response URL including the generated Responder Payload and recovers the Responder Payload, the recovery of the Responder Payload causing the initiator device to commission the joiner device to the home area network.

Switching Scheme for Opting In and Out of Multi-User Orthogonal Frequency-Division Multiple Access (18219958)

Main Inventor

Ahmed Ibrahim ElArabawy

Brief explanation

The patent application describes a method for switching between multi-user and single-user modes in a wireless network.

• The electronic device enters the multi-user mode to communicate over a shared-channel bandwidth.
• If the uplink-queue size exceeds a certain threshold, the device switches to the single-user mode.
• In the single-user mode, the device contends for a transmit channel to send uplink data.

Abstract

This document describes methods, devices, systems, and means for a switching scheme for opting in and out of multi-user orthogonal frequency-division multiple access (MU-OFDMA). In one aspect, an electronic device enters the MU-OFDMA mode to communicate via a wireless network over a shared-channel bandwidth. During the MU-OFDMA mode, the electronic device determines that an uplink-queue size is greater than a first threshold size. Responsive to the determining, the electronic device opts out of the MU-OFDMA mode and enters a single-user mode to contend for a transmit channel for transmitting uplink data.

Radio Access Technology Identifiers (17996185)

Main Inventor

Jibing Wang

Brief explanation

- This patent application describes techniques and apparatuses for managing radio access technology identifiers in wireless communication systems.

- The base station receives information about the prospective usage of air interface resources for communications over different wireless links that use different Radio Access Technologies (RATS). - Based on this information, the base station allocates the shared air interface resource between the different wireless links. - The base station then transmits a RAT-identifier-presence indicator to indicate the presence of a RAT identifier, which is used to allocate the shared air interface resource. - The RAT-identifier-presence indicator specifies the downlink air interface resources used to transmit the RAT identifier. - The base station then transmits the RAT identifier using the specified downlink air interface resources. - This technology helps in efficiently managing and allocating air interface resources in wireless communication systems that use different Radio Access Technologies.

Abstract

Techniques and apparatuses are described for radio access technology identifiers. In aspects, a base station receives air interface resource prospective usage information associated with communications over a first wireless link of at least two wireless links that use different Radio Access Technologies (RATS). The base station then allocates the sharable air interface resource between the at least two wireless links by analyzing the air interface resource prospective usage information. In aspects, the base station transmits a RAT-identifier-presence indicator that communicates a presence of a RAT identifier by indicating one or more downlink air interface resources used to transmit the RAT identifier, where the RAT identifier indicates the allocation of the sharable air interface resource between the at least two wireless links. The base station then transmits the RAT identifier using the one or more downlink air interface resources indicated by the RAT-identifier-presence indicator.

Light-Sealing Gasket with Crossbar Force Distribution (17785320)

Main Inventor

David I. Rosen

Brief explanation

- The patent application describes a light-sealing gasket with crossbar force distribution.

- The gasket is designed to be used in an electronic device with a sensor package positioned behind the display. - Its purpose is to shield the receive signals from the transmit signals, preventing signal crosstalk. - The gasket also protects the delicate panel layer of the display. - By using this gasket, manufacturers can add more features to the device and enhance the user experience.

Abstract

This document describes a light-sealing gasket with crossbar force distribution. The gasket can be used in an electronic device with a sensor package that is capable of transmitting and receiving signals and is positioned behind a display of the device. The gasket provides a shield between the receive signals and the transmit signals, prevents signal crosstalk, and protects the delicate panel layer of the display. Use of this gasket in an electronic device allows manufacturers to add more features to the device and enrich the user experience.