Abstract: Techniques are described herein for assembling/evaluating automated assistant responses for privacy concerns. In various implementations, a free-form natural language input may be received from a first user and may include a request for information pertaining to a second user. Multiple data sources may be identified that are accessible by an automated assistant to retrieve data associated with the second user. The multiple data sources may collectively include sufficient data to formulate a natural language response to the request. Respective privacy scores associated with the multiple data sources may be used to determine an aggregate privacy score associated with responding to the request. The natural language response may then be output at a client device operated by the first user in response to a determination that the aggregate privacy score associated with the natural language response satisfies a privacy criterion established for the second user with respect to the first user.
Abstract: Auto-detecting an electronic shopping basket and auto-completing offer redemption codes on the shopping basket webpage. When the user selects an item to add to the shopping basket, the shopping basket webpage loads. A plug-in detects a load event and communicates that information to an offer system. The offer system reviews the information, identifies the merchant, and determines offer codes applicable to a purchase. The offer system communicates the offer code to the plug-in, which auto-completes the code on the electronic shopping basket. The user completes the online transaction and the merchant provides a notification of completed transaction webpage. The plug-in detects a load event for the completed transaction webpage and communicates information regarding the load event to the offer system. The offer system reviews the information, identifies the offer code previously transmitted for auto-completion, marks the offer code as redeemed, and calculates the redemption rate of the transmitted offer code.
Abstract: Implementations described herein determine, for a given document generated by a given source, one or more portions of content (e.g., phrase(s), image(s), paragraph(s), etc.) of the given document that may be influenced by a source perspective of the given source. Further, implementations determine one or more additional resources that are related to the given source and that are related to the portion(s) of content of the given document. Yet further, implementations utilize the additional resource(s) to determine additional content that provides context for the portion(s) that may be influenced by a source perspective. A relationship, between the additional resource(s) and the portions of the given document, can be defined. Based on the relationship being defined, the additional content can be caused to be rendered at a client device in response to the client device accessing the given document.
Abstract: At least one aspect of the present disclosure is directed to systems and methods of selecting and acknowledging content to broadcast. A system can receive, at a first time, a request for content to broadcast identifying a content publisher. The system can obtain cluster data of the content publisher corresponding to a first time, the cluster data identifying content selection metrics based on predicted characteristics of the cluster corresponding to the first time. The system can determine a subset of content items having cluster filtering criteria that satisfy the content selection metrics. The system can rank the subset of content items based on the content selection metrics to create an ordered list of content items. The system can transmit data identifying the order of the content items to the content publisher. The content publisher can insert the content into a broadcast in the order identified by the system.
Type:
Application
Filed:
April 8, 2020
Publication date:
April 21, 2022
Applicant:
GOOGLE LLC
Inventors:
Charles Alexander SOLARSKI, Davod Andrew BROWN, Stelia LOH, Akshay LAL, Tyrone Hidekazu NAKAHARA
Abstract: A method for denoising video content includes identifying a first frame block associated with a first frame of the video content. The method also includes estimating a first noise model that represents characteristics of the first frame block. The method also includes identifying at least one frame block adjacent to the first frame block. The method also includes generating a second noise model that represents characteristics of the at least one frame block adjacent to the first frame block by adjusting the first noise model based on at least one characteristic of the at least one frame block adjacent to the first frame block. The method also includes denoising the at least one frame block adjacent to the first frame block using the second noise model.
Type:
Grant
Filed:
December 4, 2017
Date of Patent:
April 19, 2022
Assignee:
GOOGLE LLC
Inventors:
Damien Kelly, Neil Birkbeck, Balineedu Adsumilli, Mohammad Izadi
Abstract: A content conversion computer system for converting static image content to dynamic content includes a memory for storing data and a processor in communication with the memory. The processor is configured to receive a static image content having a plurality of image characteristics, analyze the static image content to determine the plurality of image characteristics, determine a plurality of dynamic content characteristics used for converting the static image content to a dynamic content, and generate the dynamic content based upon the image characteristics and the dynamic content characteristics.
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for query categorization based on image results. In one aspect, a method includes receiving images from image results responsive to a query, wherein each of the images is associated with an order in the image results and respective user behavior data for the image as a search result for the first query, and associating one or more of the first images with a plurality of annotations based on analysis of the selected first images' content.
Abstract: A computer-implemented method is described that includes providing a watch defining a body and a watch face on a surface of the body, the body having one or more sensors arranged to sense user inputs in an area adjacent to the body. The method further comprises sensing a motion of an object in the area adjacent to, but not touching, the body using the one or more sensors and changing a display of a pointing element on a graphical user interface on the watch in coordination with the sensed motion.
Type:
Grant
Filed:
October 23, 2020
Date of Patent:
April 19, 2022
Assignee:
GOOGLE LLC
Inventors:
James B. Miller, Richard C. Gossweiler, III
Abstract: A method for denoising video content includes identifying a first frame block of a plurality of frame blocks associated with a first frame of the video content. The method also includes determining an average intensity value for the first frame block. The method also includes determining a first noise model that represents characteristics of the first frame block. The method also includes generating a denoising function using the average intensity value and the first noise model for the first frame block. The method further includes denoising the plurality of frame blocks using the denoising function.
Type:
Grant
Filed:
December 5, 2017
Date of Patent:
April 19, 2022
Assignee:
GOOGLE LLC
Inventors:
Neil Birkbeck, Balineedu Adsumilli, Mohammad Izadi
Abstract: Encoding an image block using a quantization parameter includes presenting, to an encoder that includes a machine-learning model, the image block and a value derived from the quantization parameter, where the value is a result of a non-linear function using the quantization parameter as input, where the non-linear function relates to a second function used to calculate, using the quantization parameter, a Lagrange multiplier that is used in a rate-distortion calculation, and where the machine-learning model is trained to output mode decision parameters for encoding the image block; obtaining the mode decision parameters from the encoder; and encoding, in a compressed bitstream, the image block using the mode decision parameters.
Type:
Grant
Filed:
May 7, 2020
Date of Patent:
April 19, 2022
Assignee:
GOOGLE LLC
Inventors:
Claudionor Coelho, Dake He, Aki Kuusela, Shan Li
Abstract: An apparatus for encoding a block of a picture includes a convolutional neural network (CNN) for determining a block partitioning of the block, the block having an N×N size and a smallest partition determined by the CNN being of size S×S. The CNN includes feature extraction layers; a concatenation layer that receives, from the feature extraction layers, first feature maps of the block, where each first feature map of the first feature maps is of the smallest possible partition size S×S of the block; and at least one classifier that is configured to infer partition decisions for sub-blocks of size (?S)×(?S) of the block, where ? is a power of 2.
Type:
Grant
Filed:
November 2, 2020
Date of Patent:
April 19, 2022
Assignee:
GOOGLE LLC
Inventors:
Claudionor Coelho, Aki Kuusela, Shan Li, Dake He
Inventors:
Mark Chang, Matthew Austin, James Buyayo, Jason Cornwell, Debbie Kim, Richard Lo, Johnathon Schlemmer, Christopher Tompkins, Megan Torkildson, Joy Barlow, Anton Volkov
Inventors:
Elizabeth Hunt, Ying Su, Bailiang Zhou, Erika Rice Scherpelz, Christopher Wahlen, Matthew Simpson, Michael Eberle-Levine, Chris Raykovich, Graham Rosser, Geoffrey Howie, Craig Prince, Sarah Needham
Inventors:
Zhijian Su, Manish Arora, Jason Bui, Sumati Prabhakar, Madeline Chan, Jennifer Cordova, Jason Gouliard, Daniel Sim, Xi Liu, Amit Chandak, Rani Mavram, Sharon Lee