中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

17884 records (took 0.037 seconds)

    Generating interactive content items based on content displayed on a computing device
    72.
    发明授权
    Generating interactive content items based on content displayed on a computing device 有权

    公开(公告)号：US10540055B2

    公开(公告)日：2020-01-21

    申请号：US15427810

    申请日：2017-02-08

    Applicant: Google Inc.

    Inventor： David Jones ,  Alison Lentz ,  Tim Wantland

    IPC: G06F3/0481

    Abstract: Methods and apparatus directed to generating one or more interactive content items based on content displayed on a computing device are described herein. In various implementations, content displayed to a user by a display of a computing device may be segmented into semantic region(s) based on respective content of the semantic region(s). User input may be received, e.g., via a biometric sensor of the computing device. The user input may indicate a desire of the user to act upon the semantic region(s). In response to the user input, interactive content item(s) corresponding to the semantic region(s) may be generated and provided for presentation to the user via output device(s) of the computing device. User interaction with a given interactive content item may cause the computing device to perform action(s) that are tailored to the semantic region that corresponds to the given interactive content item.

    Auto-prioritization of device traffic across local network
    73.
    发明授权
    Auto-prioritization of device traffic across local network 有权

    公开(公告)号：US10536345B2

    公开(公告)日：2020-01-14

    申请号：US15392576

    申请日：2016-12-28

    Applicant: Google Inc.

    Inventor： Alex Daniel Jacobson ,  Laura Marie Eidem

    IPC: H04L29/06 ,  H04L12/24 ,  H04L12/911 ,  H04L12/927 ,  G16H40/63 ,  H04L29/08 ,  H04L12/26 ,  G16H50/30 ,  H04L12/28

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for prioritizing network traffic. In one aspect, a method includes collecting, for local networks, traffic data representing communication traffic over the local network for a period of time; determining, for each of the network devices included in the networks, a device type of the network device and at least one device priority value for the network device; training a device prioritization model, using the traffic data and the device priority values of the devices, receiving, by the device prioritization model, for a local network, a list of network devices that are included in the local network; and generating, by the device prioritization model, a prioritization scheme for the local network that prioritizes device traffic among the network devices based on the device types and device priority values of the network devices.

    Adversarial training of neural networks
    75.
    发明授权
    Adversarial training of neural networks 有权

    公开(公告)号：US10521718B1

    公开(公告)日：2019-12-31

    申请号：US15279268

    申请日：2016-09-28

    Applicant: Google Inc.

    Inventor： Christian Szegedy ,  Ian Goodfellow

    IPC: G06N3/08 ,  G06N20/00

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for adversarial training of a neural network. One of the methods includes obtaining a plurality of training inputs; and training the neural network on each of the training inputs, comprising, for each of the training inputs: processing the training input using the neural network to determine a neural network output for the training input; applying a perturbation to the training input to generate an adversarial perturbation of the training input; processing the adversarial perturbation of the training input using the neural network to determine a neural network output for the adversarial perturbation; and adjusting the current values of the parameters of the neural network by performing an iteration of a neural network training procedure to optimize an adversarial objective function.

    Platform for multiple device playout
    76.
    发明授权
    Platform for multiple device playout 有权

    公开(公告)号：US10516718B2

    公开(公告)日：2019-12-24

    申请号：US14735489

    申请日：2015-06-10

    Applicant: GOOGLE INC.

    Inventor： Mikhal Shemer ,  Patrik Göran Westin

    IPC: H04L29/06 ,  H04L29/08 ,  G06F9/54

    Abstract: Provided is a platform for data devices in which the architecture and runtime parameters of the platform are adaptively updated based on real-time data collected about a network on which the platform operates, the source type (e.g., codec selection) for data being communicated between devices, the grouping/architecture of the devices, or any combination thereof. The platform is thus able to support multiple different types and configurations of data devices under varied, constantly-changing conditions. The platform offers a flexible architecture for a content management and rendering system in which multiple data devices connected via the network each play a unique role in the operation of the system. The data devices are capable of dynamically switching between different roles while the system is in active operation. The platform also includes adaptive delay capabilities as well as adaptive codec selection capabilities.

    Systems and methods to perform machine learning with feedback consistency
    78.
    发明授权
    Systems and methods to perform machine learning with feedback consistency 有权

    公开(公告)号：US10482379B2

    公开(公告)日：2019-11-19

    申请号：US15222997

    申请日：2016-07-29

    Applicant: Google Inc.

    Inventor： Jason E. Holt ,  Marcello Mathias Herreshoff

    IPC: G06N3/08 ,  G06N3/04

    Abstract: The present disclosure provides systems and methods that enable training of an encoder model based on a decoder model that performs an inverse transformation relative to the encoder model. In one example, an encoder model can receive a first set of inputs and output a first set of outputs. The encoder model can be a neural network. The decoder model can receive the first set of outputs and output a second set of outputs. A loss function can describe a difference between the first set of inputs and the second set of outputs. According to an aspect of the present disclosure, the loss function can be sequentially backpropagated through the decoder model without modifying the decoder model and then through the encoder model while modifying the encoder model, thereby training the encoder model. Thus, an encoder model can be trained to have enforced consistency relative to the inverse decoder model.

    Predictive insertion of graphical objects in a development environment
    80.
    发明授权
    Predictive insertion of graphical objects in a development environment 有权

    公开(公告)号：US10466863B1

    公开(公告)日：2019-11-05

    申请号：US15170260

    申请日：2016-06-01

    Applicant: Google Inc.

    Inventor： Romain P. Guy

    IPC: G06F3/0482 ,  G06F8/38 ,  G06F8/33 ,  G06F3/0484 ,  G06F3/0488 ,  G06F8/00

    Abstract: An example method includes outputting, by a computing device and for display in a graphical development environment used during development of a software application, a graphical user interface associated with the software application, receiving, by the computing device, a development specification that associates a region of the graphical user interface with one or more candidate graphical objects for insertion into the graphical user interface, and receiving, by the computing device, an indication of a selection of the region of the graphical user interface. The example method further includes determining, by the computing device, based at least in part on the development specification and the indication of the selection of the region of the graphical user interface, a graphical object from the one or more candidate graphical objects, and outputting, by the computing device and for display at the region of the graphical user interface, an indication of the graphical object.

Patent Agency Ranking