Patents by Inventor Kexia Tang

Kexia Tang 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).

  • Efficient structured data exploration with a combination of bivariate metric and centrality measures
    Patent number: 9858333
    Abstract: According to one exemplary embodiment, a method for exploring a structured data set is provided. The method may include receiving a plurality of bivariate pairs and an input bivariate pair, wherein the plurality of bivariate pairs and the input bivariate pair are based on the structured data set. The method may include constructing a graph having a plurality of nodes and a plurality of edges based on the received plurality of bivariate pairs and input bivariate pair. The method may include constructing an adjacency matrix based on the constructed graph. The method may include calculating a centrality for each node based on the constructed matrix. The method may include constructing an orthogonal list based on the plurality of bivariate pairs and the input bivariate pair. The method may include ordering the orthogonal list based on the calculated centrality of each node within the plurality of nodes.
    Type: Grant
    Filed: March 8, 2016
    Date of Patent: January 2, 2018
    Assignee: International Business Machines Corporation
    Inventor: Kexia Tang
  • Efficient structured data exploration with a combination of bivariate metric and centrality measures
    Patent number: 9858331
    Abstract: According to one exemplary embodiment, a method for exploring a structured data set is provided. The method may include receiving a plurality of bivariate pairs and an input bivariate pair, wherein the plurality of bivariate pairs and the input bivariate pair are based on the structured data set. The method may include constructing a graph having a plurality of nodes and a plurality of edges based on the received plurality of bivariate pairs and input bivariate pair. The method may include constructing an adjacency matrix based on the constructed graph. The method may include calculating a centrality for each node based on the constructed matrix. The method may include constructing an orthogonal list based on the plurality of bivariate pairs and the input bivariate pair. The method may include ordering the orthogonal list based on the calculated centrality of each node within the plurality of nodes.
    Type: Grant
    Filed: February 5, 2015
    Date of Patent: January 2, 2018
    Assignee: International Business Machines Corporation
    Inventor: Kexia Tang
  • EFFICIENT STRUCTURED DATA EXPLORATION WITH A COMBINATION OF BIVARIATE METRIC AND CENTRALITY MEASURES
    Publication number: 20160232212
    Abstract: According to one exemplary embodiment, a method for exploring a structured data set is provided. The method may include receiving a plurality of bivariate pairs and an input bivariate pair, wherein the plurality of bivariate pairs and the input bivariate pair are based on the structured data set. The method may include constructing a graph having a plurality of nodes and a plurality of edges based on the received plurality of bivariate pairs and input bivariate pair. The method may include constructing an adjacency matrix based on the constructed graph. The method may include calculating a centrality for each node based on the constructed matrix. The method may include constructing an orthogonal list based on the plurality of bivariate pairs and the input bivariate pair. The method may include ordering the orthogonal list based on the calculated centrality of each node within the plurality of nodes.
    Type: Application
    Filed: February 5, 2015
    Publication date: August 11, 2016
    Inventor: Kexia Tang
  • EFFICIENT STRUCTURED DATA EXPLORATION WITH A COMBINATION OF BIVARIATE METRIC AND CENTRALITY MEASURES
    Publication number: 20160232227
    Abstract: According to one exemplary embodiment, a method for exploring a structured data set is provided. The method may include receiving a plurality of bivariate pairs and an input bivariate pair, wherein the plurality of bivariate pairs and the input bivariate pair are based on the structured data set. The method may include constructing a graph having a plurality of nodes and a plurality of edges based on the received plurality of bivariate pairs and input bivariate pair. The method may include constructing an adjacency matrix based on the constructed graph. The method may include calculating a centrality for each node based on the constructed matrix. The method may include constructing an orthogonal list based on the plurality of bivariate pairs and the input bivariate pair. The method may include ordering the orthogonal list based on the calculated centrality of each node within the plurality of nodes.
    Type: Application
    Filed: March 8, 2016
    Publication date: August 11, 2016
    Inventor: Kexia Tang