Detecting an event from signals in a listening area

• US 10,353,934 B1
• Filed: 09/14/2018
• Issued: 07/16/2019
• Est. Priority Date: 04/27/2018
• Status: Expired due to Fees

• Current Assignee: Banjo, Inc.
• Original Assignee: Banjo, Inc.
• Inventors: Mehta, Rish, Patton, Damien, Gratton, Christian, Leung, K W Justin, Gowda, Varun
• Primary Examiner(s): Sirjani, Fariba
• Application Number:
  US16/131,637
• Time in Patent Office: 305 Days
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/381 using identifiers, e.g. barcodes, RFIDs for URLs G06F16/9554
• CPC Class Codes: G06F 16/5846 using extracted text
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching
• 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]
• CPC Class Codes: H04W 76/50 for emergency connections

Abstract

The present invention extends to methods, systems, and computer program products for detecting an event from signals in a listening area. Listening area formation is triggered based on detecting a potential event from a normalized signal, based on characteristics of a normalized signal, or based on a signal pattern anomaly. A geo cell database is queried with search terms derived from one or more normalized signals. A geo cell subset is returned from the geo cell database. A listening area is formed from the geo cells included in the geo cell subset. A listener monitors an additional normalized signal in the listening area. An event is detected and/or validated (or rejected) based on the additional normalized signal.

Claims

1. A method comprising:

receiving a raw signal including source data from a signal source;

applying a transdimensionality transform in a Time, Location, Context (TLC) dimensional model to the raw signal lowering the dimensionality of the source data and re-encoding the raw signal into a Time, Location, Context (TLC) normalized signal of lower dimensionality, wherein context of the Time, Location, Context (TLC) normalized signal indicates an event type and is derived from text obtained by applying natural language processing (NLP) to text of content of the Time, Location, Context (TLC) normalized signal;

detecting a potential event and identifying the Time, Location, Context (TLC) normalized signal as a trigger signal when characteristics of the Time, Location, Context (TLC) normalized signal satisfy first detection model thresholds;

deriving search terms from content of the trigger signal by applying natural language processing (NLP) to text of the content;

querying a geo cell database with the search terms;

receiving a list of geo cells that correspond to the search terms;

formulating a geo cell listening area from the list of geo cells;

monitoring the geo cell listening area for signals, related to the trigger signal, according to second detection model thresholds that are less stringent than the first detection model thresholds;

detecting a related signal in the geo cell listening area, the related signal being a related Time, Location, Context (TLC) normalized signal from another signal source including other normalized data of the lower dimensionality, wherein characteristics of the related signal satisfy the second detection model thresholds;

obtaining a distance between dimensions of the trigger signal and corresponding dimensions of the related signal; and

validating the potential event as an actual event of the event type based on characteristics of the trigger signal, characteristics of the related signal, and the distance obtained between the dimensions of the trigger signal and the corresponding dimensions of the related signal.

2. The method of claim 1, wherein obtaining a distance between dimensions of the trigger signal and corresponding dimensions of the related signal comprise comparing the dimensions of the trigger signal to the corresponding dimensions of the related signal.

3. The method of claim 1, wherein validating the potential event as an actual event comprises validating the potential event as an actual event based on one or more of:

a time dimension, a location dimension, or a context dimension included in the other Time, Location, Context (TLC) normalized signal.

4. The method of claim 1, wherein deriving search terms from content of the trigger signal comprises applying the natural language processing (NLP) to derive the search terms from the text obtained by audio processing of audio content.

5. The method of claim 1, wherein deriving search terms from content of the trigger signal comprises recognizing the text in an image.

6. The method of claim 1, further comprising determining the size of the geo cell listening area based on a location distance threshold associated with the event type.

7. The method of claim 1, further comprising:

expanding the geo cell listening area into an expanded geo cell listening area in response to monitoring the related signal;

detecting a further Time, Location, Context (TLC) normalized signal in the expanded geo cell listening area; and

wherein validating the potential event as an actual event further comprises validating the potential event as the actual event based on characteristics of the further Time, Location, Context (TLC) normalized signal.

8. A system comprising:

a processor;

system memory coupled to the processor and storing instructions configured to cause the processor to;

receive a raw signal including source data from a signal source;

apply a transdimensionality transform in a Time, Location, Context (TLC) dimensional model to the raw signal lowering the dimensionality of the source data and re-encoding the raw signal into a Time, Location, Context (TLC) normalized signal of lower dimensionality, wherein context of the Time, Location, Context (TLC) normalized signal indicates an event type and is derived from text obtained by applying natural language processing (NLP) to text of content of the Time, Location, Context (TLC) normalized signal;

detect a potential event and identify the Time, Location, Context (TLC) normalized signal as a trigger signal when characteristics of the Time, Location, Context (TLC) normalized signal satisfy first detection model thresholds;

derive search terms from content of the signal by applying natural language processing (NLP) to text of the content;

query a geo cell database with the search terms;

receive a list of geo cells that correspond to the search terms;

formulate a geo cell listening area from the list of geo cells;

monitor the geo cell listening area for signals, related to the trigger signal, according to second detection model thresholds that are less stringent than the first detection model thresholds;

detect a related signal in the geo cell listening area, the related signal being a related Time, Location, Context (TLC) normalized signal from another signal source including other normalized data of the lower dimensionality, wherein characteristics of the related signal satisfy the second detection model thresholds;

obtain a distance between dimensions of the trigger signal and corresponding dimensions of the related signal; and

validate the potential event as an actual event of the event type based on characteristics of the trigger signal, characteristics of the related signal, and the distance obtained between the dimensions of the trigger signal and the corresponding dimensions of the related signal.

9. The system of claim 8, wherein instructions configured to obtain a distance between dimensions of the trigger signal and corresponding dimensions of the related signal comprise instructions configured to compare the dimensions of the trigger signal to the corresponding dimensions of the related signal.

10. The system of claim 8, wherein instructions configured to validate the potential event as an actual event comprise instructions configured to validate the potential event as an actual event based on one or more of:

a time dimension, a location dimension, or a context dimension included in the other Time, Location, Context (TLC) normalized signal.

11. The system of claim 8, wherein instructions configured to derive search terms from content of the trigger signal comprise instructions configured to apply the natural language processing (NLP) to derive the search terms from text obtained by audio processing of audio content.

12. The system of claim 8, wherein instructions configured to derive search terms from content of the trigger signal comprise instructions configured to recognize the text in an image.

13. The system of claim 8, further comprising instructions configured to determine the size of the geo cell listening area based on a location distance threshold associated with the event type.

14. The system of claim 8, further comprising instructions configured to:

expand the geo cell listening area into an expanded geo cell listening area in response to monitoring the related signal;

detect a further Time, Location, Context (TLC) normalized signal in the expanded geo cell listening area; and

wherein instructions configured to validate the potential event as an actual event comprise instructions configured to validate the potential event as the actual event based on characteristics of the further Time, Location, Context (TLC) normalized signal.