×

Methods and systems of detection of most relevant insights for large volume query-based social data stream

  • US 9,634,909 B2
  • Filed: 04/30/2013
  • Issued: 04/25/2017
  • Est. Priority Date: 04/30/2012
  • Status: Active Grant
First Claim
Patent Images

1. A system comprising a non-transitory machine-readable medium having instructions stored thereon for execution by a processor to perform a method for detection of the most relevant insights for any large volume query-based social data stream comprising the steps of:

  • interfacing with one or more streaming social data sources;

    collecting one or more mentions that match a search query;

    storing said mentions on a first server;

    enhancing said mentions with additional information to produce enhanced mentions;

    storing said enhanced mentions on a second server;

    filtering said enhanced mentions into filtered streams;

    aggregating statistical data of said filtered streams; and

    analyzing for an anomaly in the statistical data of each of said filtered streams to detect the most relevant insights using a hybrid statistical approach adapted to the volume and steadiness of the data of the filtered streams, such that the most relevant insights for the streaming social data sources are detected and a real-time alert may be generated based on the detected anomaly or insight.

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