Patents by Inventor Shibi He

Shibi He 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).

  • DATA RETRIEVAL USING REINFORCED CO-LEARNING FOR SEMI-SUPERVISED RANKING
    Publication number: 20240127064
    Abstract: A computer-implement method comprises: training a classifier with labeled data from a dataset; classifying, by the trained classifier, unlabeled data from the dataset; providing, by the classifier to a policy gradient, a reward signal for each data/query pair; transferring, by the classifier to a ranker, learning; training, by the policy gradient, the ranker; ranking data from the dataset based on a query; and retrieving data from the ranked data in response to the query.
    Type: Application
    Filed: December 18, 2023
    Publication date: April 18, 2024
    Inventors: Shibi He, Yanen Li, Ning Xu
  • Data retrieval using reinforced co-learning for semi-supervised ranking
    Patent number: 11893489
    Abstract: A computer-implement method comprises: training a classifier with labeled data from a dataset; classifying, by the trained classifier, unlabeled data from the dataset; providing, by the classifier to a policy gradient, a reward signal for each data/query pair; transferring, by the classifier to a ranker, learning; training, by the policy gradient, the ranker; ranking data from the dataset based on a query; and retrieving data from the ranked data in response to the query.
    Type: Grant
    Filed: October 24, 2022
    Date of Patent: February 6, 2024
    Assignee: SNAP INC.
    Inventors: Shibi He, Yanen Li, Ning Xu
  • DATA RETRIEVAL USING REINFORCED CO-LEARNING FOR SEMI-SUPERVISED RANKING
    Publication number: 20230053009
    Abstract: A computer-implement method comprises: training a classifier with labeled data from a dataset; classifying, by the trained classifier, unlabeled data from the dataset; providing, by the classifier to a policy gradient, a reward signal for each data/query pair; transferring, by the classifier to a ranker, learning; training, by the policy gradient, the ranker; ranking data from the dataset based on a query; and retrieving data from the ranked data in response to the query.
    Type: Application
    Filed: October 24, 2022
    Publication date: February 16, 2023
    Inventors: Shibi He, Yanen Li, Ning Xu
  • Data retrieval using reinforced co-learning for semi-supervised ranking
    Patent number: 11544553
    Abstract: A computer-implement method comprises: training a classifier with labeled data from a dataset; classifying, by the trained classifier, unlabeled data from the dataset; providing, by the classifier to a policy gradient, a reward signal for each data/query pair; transferring, by the classifier to a ranker, learning; training, by the policy gradient, the ranker; ranking data from the dataset based on a query; and retrieving data from the ranked data in response to the query.
    Type: Grant
    Filed: June 21, 2019
    Date of Patent: January 3, 2023
    Assignee: Snap Inc.
    Inventors: Shibi He, Yanen Li, Ning Xu