×

Automatic segmentation of video

  • US 8,423,555 B2
  • Filed: 07/09/2010
  • Issued: 04/16/2013
  • Est. Priority Date: 07/09/2010
  • Status: Active Grant
First Claim
Patent Images

1. A method comprising:

  • receiving text associated with a content item, the text including a plurality of term strings, each term string including one or more terms;

    determining, by a computing device, a set of relevance intervals for a corresponding set of terms in the text, wherein each relevance interval of the set of relevance intervals identifies one or more sections of the content item that are relevant to a corresponding term;

    generating a first set of nodes for a first term string from the plurality of term strings, wherein the first set of nodes includes a node for each term in the first term string, and at least one node for a term different from the terms in the first term string but whose corresponding relevance interval includes the first term string;

    generating a second set of nodes for a second term string from the plurality of term strings, wherein the second set of nodes includes a node for each term in the second term string, and at least one node for a term different from the terms in the second term string but whose corresponding relevance interval includes the second term string; and

    determining a plurality of connections between nodes in the first set of nodes and the second set of nodes, wherein the plurality of connections includes a subset for a first node from the first set of nodes, wherein the subset for the first node includes a connection for each node from the second set of nodes; and

    using the first set of nodes, second set of nodes or plurality of connections to identify one or more segment boundaries within the content item.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×