×

Detecting events from features derived from multiple ingested signals

  • US 10,311,129 B1
  • Filed: 11/29/2018
  • Issued: 06/04/2019
  • Est. Priority Date: 02/09/2018
  • Status: Expired due to Fees
First Claim
Patent Images

1. A method comprising:

  • receiving a first Time, Location, Context (TLC) normalized signal including a first time dimension, a first location dimension, and a first context dimension, the first context dimension including a first single source probability representing at least a first approximate probability of a real-world event of a specified event type;

    deriving first one or more features from the first TLC normalized signal including from the first single source probability;

    determining that the first one or more features, including the first single source probability, provide insufficient evidence to be identified as the real-world event of the specified event type;

    receiving a second Time, Location, Context (TLC) normalized signal including a second time dimension, a second location dimension, and a second context dimension, the second context dimension including a second single source probability representing at least a second approximate probability that the real-world event of the specified event type;

    deriving second one or more features from the second TLC normalized signal including from the second signal source probability;

    aggregating the first single source probability and the second single source probability into a multisource probability; and

    detecting the real-world event from evidence provided by the multisource probability, including the multisource probability exceeding a threshold probability associated with the event type.

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