Patents by Inventor Yi Chew

Yi Chew has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 12073292
    Abstract: Balancing content distribution between a machine learning model and a statistical model provides a baseline assurance in combination with the benefits of a well-trained machine learning model for content selection. In some implementations, a server receiving requests for a content item assigns a first proportion of the received requests to a first group and assigns remaining requests to a second group. The server uses a machine learning model to select variations of the requested content item for responding to requests assigned to the first group and uses a statistical model to select content variations for requests assigned to the second group. The server obtains performance information, e.g., acceptance rates for the different variations, and compares performance of the different models used for content selection. Audience share assigned to the machine learning model is increased when it outperforms the statistical model and decreased when it underperforms the statistical model.
    Type: Grant
    Filed: January 24, 2017
    Date of Patent: August 27, 2024
    Assignee: GOOGLE LLC
    Inventors: Sue Yi Chew, Deepak Ramamurthi Sivaramapuram Chandrasekaran, Bo Fu, Prachi Gupta, Kunal Jain, Thomas Price, Sarvjeet Singh, Jierui Xie
  • Publication number: 20190311287
    Abstract: Balancing content distribution between a machine learning model and a statistical model provides a baseline assurance in combination with the benefits of a well-trained machine learning model for content selection. In some implementations, a server receiving requests for a content item assigns a first proportion of the received requests to a first group and assigns remaining requests to a second group. The server uses a machine learning model to select variations of the requested content item for responding to requests assigned to the first group and uses a statistical model to select content variations for requests assigned to the second group. The server obtains performance information, e.g., acceptance rates for the different variations, and compares performance of the different models used for content selection. Audience share assigned to the machine learning model is increased when it outperforms the statistical model and decreased when it underperforms the statistical model.
    Type: Application
    Filed: January 24, 2017
    Publication date: October 10, 2019
    Applicant: Google LLC
    Inventors: Sue Yi Chew, Deepak Ramamurthi Sivaramapuram Chandrasekaran, Bo Fu, Prachi Gupta, Kunal Jain, Thomas Price, Sarvjeet Singh, Jierui Xie
  • Publication number: 20070232497
    Abstract: The present invention provides a water soluble tape for controlled release of at least one active ingredient, a water soluble adhesive tape for controlled release of at least one active ingredient, a method for manufacturing a water soluble tape for controlled release of at least one active ingredient, and a method for utilizing the condensate water for cleansing and disinfection purposes.
    Type: Application
    Filed: April 4, 2006
    Publication date: October 4, 2007
    Inventors: Yiwen Chew, Yi Chew
  • Publication number: 20060165745
    Abstract: The present invention provides tablets for treatment of aqueous environment that release at least one active ingredient in a sustained manner so as to provide the treated aqueous environment with the at least one active ingredient for a long period with a single dose. The present invention also provides methods for making the sustained release tablets.
    Type: Application
    Filed: January 21, 2005
    Publication date: July 27, 2006
    Inventors: Yiwen Chew, Yi Chew