Normalizing insufficient signals based on additional information

• US 10,268,642 B1
• Filed: 10/25/2018
• Issued: 04/23/2019
• Est. Priority Date: 04/27/2018
• Status: Expired due to Fees

• Current Assignee: Banjo, Inc.
• Original Assignee: Banjo, Inc.
• Inventors: Leung, KW Justin, Urbach, Michael Avner, Patton, Damien, Gratton, Christian
• Primary Examiner(s): Nguyen, Cam Linh T
• Application Number:
  US16/170,325
• Time in Patent Office: 180 Days
• Field of Search: 707736
• CPC Class Codes: G06F 16/258 Data format conversion from or to a database
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 9/542 Event management; Broadcasting; Multicasting; Notifications
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/90 Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS]

Abstract

The present invention extends to methods, systems, and computer program products for normalizing insufficient signals based on additional information. Evidence of an event is detected from a raw signal. It is determined signal characteristics of the raw signal are insufficient to normalize the raw signal along at least one of: a time, location, or context dimension into a Time, Location, Context (TLC) format. In one aspect, an additional raw signal related to the detected evidence is accessed from another signal source. In another aspect, a previously detected event related to the detected evidence is received from a geo cell database. The raw signal is normalized into the Time, Location, Context (TLC) format, including deriving at least one of: the time dimension, the location dimension, or the context dimension from a combination of the signal characteristics and characteristics of the other signal and/or characteristics of the previously detected event.

Claims

1. A computer-implemented signal normalization method comprising:

ingesting a raw signal including a time stamp, an indication of a signal type, an indication of a signal source, and content from the signal source;

detecting evidence of an event from the content;

determining that signal characteristics of the raw signal are insufficient to normalize the raw signal along at least one of;

a time dimension, a location dimension, or a context dimension into a Time, Location, Context (TLC) format;

triggering a signal request requesting additional signals related to the detected evidence in response to determining that the signal characteristics are insufficient;

accessing an additional raw signal related to the detected evidence from another signal source; and

normalizing the raw signal into the Time, Location, Context (TLC) format including deriving at least one of;

the time dimension, the location dimension, or the context dimension from a combination of the signal characteristics and characteristics of the additional raw signal.

2. The method of claim 1, wherein determining that signal characteristics of the raw signal are insufficient to normalize the raw signal comprises determining that that the raw signal lacks sufficiently accurate location information.

3. The method of claim 1, wherein determining that signal characteristics of the raw signal are insufficient to normalize the raw signal comprises determining that that the raw signal lacks sufficiently accurate context information.

4. The method of claim 1, further comprising sending the signal request to one or more other signal sources.

5. The method of claim 4, wherein accessing an additional raw signal related to the detected evidence from another signal source comprises accessing an additional raw signal returned from the one or more other signal sources in response to the signal request.

6. The method of claim 1, wherein normalizing the raw signal into the Time, Location, Context (TLC) format comprises deriving the location dimension of the raw signal from a combination of the signal characteristics and characteristics of the additional raw signal.

7. The method of claim 1, further comprising detecting an event of interest to one or more entities based on the time dimension, the location dimension, or the context dimension of the normalized raw signal.

8. A computer-implemented signal normalization method comprising:

ingesting a raw signal including a time stamp, an indication of a signal type, an indication of a signal source, and content from a signal source;

detecting evidence of an event at a location from the content;

determining that signal characteristics of the raw signal are insufficient to normalize the raw signal along at least one of;

a time dimension, a location dimension, or a context dimension into a Time, Location, Context (TLC) format;

requesting previously detected events at or near the location of the ingested raw signal from a geo cell database in response to determining that the signal characteristics are insufficient;

receiving a previously detected event related to the detected evidence from the geo cell database; and

normalizing the raw signal into the Time, Location, Context (TLC) format including deriving at least one of;

the time dimension, the location dimension, or the context dimension from a combination of the signal characteristics and characteristics of the previously detected event.

9. The method of claim 8, wherein determining that signal characteristics of the raw signal are insufficient to normalize the raw signal comprises determining that that the raw signal lacks sufficiently accurate location information.

10. The method of claim 8, wherein determining that signal characteristics of the raw signal are insufficient to normalize the raw signal comprises determining that the raw signal lacks sufficiently accurate context information.

11. The method of claim 8, wherein requesting previously detected events comprises:

formulating a query that includes the detected evidence; and

sending the query to the geo cell database.

12. The method of claim 8, wherein normalizing the raw signal into the Time, Location, Context (TLC) format comprises deriving the location dimension of the raw signal from a combination of the signal characteristics and characteristics of the previously detected event.

13. The method of claim 8, further comprising detecting an event of interest to one or more entities based on the time dimension, the location dimension, or the context dimension of the normalized raw signal.

14. A computer-implemented signal normalization method comprising:

ingesting a raw signal including a time stamp, an indication of a signal type, an indication of a signal source, and content from a signal source;

detecting evidence of an event at a location from the content;

determining that signal characteristics of the raw signal are insufficient to normalize the raw signal along at least one of;

a time dimension, a location dimension, or a context dimension into a Time, Location, Context (TLC) format;

obtaining supplemental information related to the detected evidence from an additional raw signal and a previously detected event;

enriching the raw signal with the supplemental information; and

normalizing the raw signal into the Time, Location, Context (TLC) format including deriving at least one of;

the time dimension, the location dimension, or the context dimension from a combination of the signal characteristics and the supplemental information.

15. The method of claim 14, further comprising:

detecting an event of interest to one or more entities based on the time dimension, the location dimension, or the context dimension of the normalized raw signal; and

notifying the one or more entities about the event of interest.