Patents by Inventor Wenrong Zeng

Wenrong Zeng 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: 11580330
    Abstract: Techniques for building a machine learning framework with tracking, model building and maintenance, and feedback loop are provided. In one technique, a prediction model is generated based on features of multiple entities. For each entity indicated in a first database, multiple feature values are identified, which include feature values stored in the first database and feature values based on sub-entity data regarding individuals associated with the entity. The feature values are input into the prediction model to generate a score for the entity. Based on the score, a determination is made whether to add, to a second database, a record for that entity. The second database is analyzed to identify other entities. For each such entity, a determination is made whether to generate a training instance; if so, a training instance is generated and added to training data, which is used to generate another prediction model.
    Type: Grant
    Filed: December 28, 2018
    Date of Patent: February 14, 2023
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Wenrong Zeng, Jiaxing Huang, Juan Wang
  • Publication number: 20200210771
    Abstract: Techniques for building a machine learning framework with tracking, model building and maintenance, and feedback loop are provided. In one technique, a prediction model is generated based on features of multiple entities. For each entity indicated in a first database, multiple feature values are identified, which include feature values stored in the first database and feature values based on sub-entity data regarding individuals associated with the entity. The feature values are input into the prediction model to generate a score for the entity. Based on the score, a determination is made whether to add, to a second database, a record for that entity. The second database is analyzed to identify other entities. For each such entity, a determination is made whether to generate a training instance; if so, a training instance is generated and added to training data, which is used to generate another prediction model.
    Type: Application
    Filed: December 28, 2018
    Publication date: July 2, 2020
    Inventors: Wenrong Zeng, Jiaxing Huang, Juan Wang
  • Publication number: 20180211268
    Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a set of predicted growth rates for a first set of customers of a product. Next, the system uses a set of features comprising the predicted growth rates to generate a set of customer segments for the product, wherein each customer segment in the set of customer segments includes a similar growth rate and a similar potential spending. For each customer segment in the set of customer segments, the system uses the similar growth rate and the similar potential spending to calculate a customer lifetime value (CLV) for the customer segment. Finally, the system outputs the CLV with a second set of customers assigned to the customer segment for use in managing sales activity with the second set of customers.
    Type: Application
    Filed: January 20, 2017
    Publication date: July 26, 2018
    Applicant: LinkedIn Corporation
    Inventors: Xing Zhou, Wenrong Zeng, Juan Wang
  • Publication number: 20170345035
    Abstract: In an example embodiment, a server accesses, for a plurality of customer accounts within a professional networking service, a plurality of features of the customer accounts stored with the professional networking service. The server accesses, for the plurality of customer accounts within the professional networking service, past sales records of products from the professional networking service to the plurality of employer accounts. The server determines, based on the past sales records and based on one or more features from the plurality of features, a product to upsell or cross-sell to a specific customer account. The server provides, as a digital transmission, indicia of the one or more features and the determined product.
    Type: Application
    Filed: May 31, 2016
    Publication date: November 30, 2017
    Inventors: Wenrong Zeng, Wei Di, Julie Wang, Yiying Cheng
  • Patent number: 5523026
    Abstract: The present invention relates to a new type NLO crystal Strontium Beryllatoborate (Chemical formula Sr.sub.2 Be.sub.2 B.sub.2 O.sub.7, abbr. SBBO). The SBBO compound is synthesized by chemical reaction of solid state in high temperature sintering, Its chemical reaction equation is:2SrCO.sub.3 +2BeO+2H.sub.3 BO.sub.3 .fwdarw.Sr.sub.2 Be.sub.2 B.sub.2 O.sub.7 +2CO.sub.2 +3H.sub.2 OA flux method is applied to the growth of single crystal of Strontium Beryllatoborate, in which SrB.sub.2 O.sub.4, NaF and other fluorides were used as flux solvents. The result of measurement indicated that this compound has following structural and physical characteristics: space group: P6.sub.3 (C.sub.6.sup.6) point group: C .sub.6, unit cell: a=4.663(3) .ANG., c=15.311(7) .ANG.,z=2, V=283.3(.ANG.).sup.3.
    Type: Grant
    Filed: April 17, 1995
    Date of Patent: June 4, 1996
    Inventors: Chuangtian Chen, Baichang Wu, Yebin Wang, Wenrong Zeng, Linhua Yu, Qun Zou