Patents by Inventor Yuhui Shi

Yuhui Shi 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: 10565551
    Abstract: A system for selecting items to be stored in a warehouse from a list of candidate items. The system includes a computing device having a processor and a storage device storing computer executable code. The executed code is configured to: assign scores to the respective candidate items based on an item selection model; and select items from the candidate items to be stored in the warehouse according to the assigned scores under a capacity limit of the warehouse. The item selection model is configured with an Artificial Neural Network (ANN), having item data for an item as input and a score for that item as output. The score represents a probability that the item is to be stored in the warehouse. The ANN is trained by historical orders with an objective of maximizing a probability that the orders have their respective item(s) all stored in the same warehouse.
    Type: Grant
    Filed: May 9, 2018
    Date of Patent: February 18, 2020
    Assignees: Beijing Jingdong Shangke Information Technology Co., Ltd., JD.com American Technologies Corporation
    Inventors: Yuhui Shi, Yixiong Chen, Chaofeng Li, Di Wu
  • Publication number: 20190347607
    Abstract: A system for selecting items to be stored in a warehouse from a list of candidate items. The system includes a computing device having a processor and a storage device storing computer executable code. The executed code is configured to: assign scores to the respective candidate items based on an item selection model; and select items from the candidate items to be stored in the warehouse according to the assigned scores under a capacity limit of the warehouse. The item selection model is configured with an Artificial Neural Network (ANN), having item data for an item as input and a score for that item as output. The score represents a probability that the item is to be stored in the warehouse. The ANN is trained by historical orders with an objective of maximizing a probability that the orders have their respective item(s) all stored in the same warehouse.
    Type: Application
    Filed: May 9, 2018
    Publication date: November 14, 2019
    Inventors: Yuhui Shi, Yixiong Chen, Chaofeng Li, Di Wu
  • Patent number: 9826759
    Abstract: A composition and method for an avenanthramide-enriched, oat-based product having improved health effects. The oat-based product includes an avenanthramide ingredient having avenanthramides 2c:2p:2f in ratios comprising at least one of 1:1:1 or 1:2:2. More particularly, the avenanthramide ingredient may be derived synthetically or recovered from processing raw oats into constituent oat fractions.
    Type: Grant
    Filed: May 21, 2014
    Date of Patent: November 28, 2017
    Assignee: The Quaker Oats Company
    Inventors: YiFang Chu, Jodee Johnson, Marianne O'Shea, Yuhui Shi
  • Publication number: 20150335045
    Abstract: A composition and method for an avenanthramide-enriched, oat-based product having improved health effects. The oat-based product includes an avenanthramide ingredient having avenanthramides 2c:2p:2f in ratios comprising at least one of 1:1:1 or 1:2:2. More particularly, the avenanthramide ingredient may be derived synthetically or recovered from processing raw oats into constituent oat fractions.
    Type: Application
    Filed: May 21, 2014
    Publication date: November 26, 2015
    Applicant: THE QUAKER OATS COMPANY
    Inventors: YiFang CHU, Jodee JOHNSON, Marianne O'SHEA, Yuhui SHI
  • Patent number: 7692558
    Abstract: Apparatus, and an associated method, for providing traffic route visualization. An electronic map device creates a map that is displayable at a user display of a user interface. The map is created through the access of a traffic image data base and a traffic information data base. Information stored at the data bases is obtained in a collaborative effort to provide and maintain updated information thereat. Images stored at the image data base comprise actual image files or photo realistic images that are consolidated together with traffic information. The resultant map is of characteristics permitting quick comprehension by a viewer thereof.
    Type: Grant
    Filed: August 1, 2007
    Date of Patent: April 6, 2010
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: Yuhui Shi, Kas Kasravi
  • Publication number: 20090033519
    Abstract: Apparatus, and an associated method, for providing traffic route visualization. An electronic map device creates a map that is displayable at a user display of a user interface. The map is created through the access of a traffic image data base and a traffic information data base. Information stored at the data bases is obtained in a collaborative effort to provide and maintain updated information thereat. Images stored at the image data base comprise actual image files or photo realistic images that are consolidated together with traffic information. The resultant map is of characteristics permitting quick comprehension by a viewer thereof.
    Type: Application
    Filed: August 1, 2007
    Publication date: February 5, 2009
    Applicant: ELECTRONIC DATA SYSTEMS CORPORATION
    Inventors: YUHUI SHI, KAS KASRAVI
  • Patent number: 6516309
    Abstract: A method of evolving a neural network that includes a plurality of processing elements interconnected by a plurality of weighted connections includes the step of obtaining a definition for the neural network by evolving a plurality of weights for the plurality of weighted connections, and evolving a plurality of activation function parameters associated with the plurality of processing elements. Another step of the method includes determining whether the definition for the neural network may be simplified based upon at least one activation function parameter of the plurality of activation function parameters. Yet another step of the method includes updating the definition for the neural network in response to determining that the definition for the neural network may be simplified. The method utilizes particle swarm optimization techniques to evolve the plurality of weights and the plurality of activation parameters.
    Type: Grant
    Filed: July 14, 1999
    Date of Patent: February 4, 2003
    Assignee: Advanced Research & Technology Institute
    Inventors: Russell C. Eberhart, Yuhui Shi