Detecting and validating planned event information

• US 10,212,572 B1
• Filed: 09/05/2018
• Issued: 02/19/2019
• Est. Priority Date: 02/09/2018
• Status: Expired due to Fees

• Current Assignee: Banjo, Inc.
• Original Assignee: Banjo, Inc.
• Inventors: Patton, Damien, Newman, Joshua J., Bruckhaus, Tilmann
• Primary Examiner(s): Butt, Walli Z
• Application Number:
  US16/121,917
• Time in Patent Office: 167 Days
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 9/542 Event management; Broadcasting; Multicasting; Notifications
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06V 10/32 Normalisation of the pattern dimensions
• CPC Class Codes: G06V 20/13 Satellite images
• CPC Class Codes: G06V 20/44 Event detection
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: H04W 4/02 Services making use of location information
• 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 detecting and validating planned event information. A plurality of normalized signals is accessed. Planned event data across the plurality of normalized signals is checked for inconsistencies. Any inconsistencies are resolved in an automated fashion, for example, through reference to databases containing additional information. A planned event can be detected/validated from concurring and/or resolved planned event data. A validator can refer to an event history database and/or a planning system to validate a possible planned event as an actual planned event.

Claims

1. A method comprising:

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

applying a transform to re-code the source data and reduce the dimensionality of the raw signal into a Time, Location, Context (TLC) normalized signal including a Time dimension, a Location dimension, and Context dimension;

detecting a possible planned event in an event category based on characteristics of the Time, Location, Context (TLC) normalized signal;

deriving a venue of the possible planned event based on characteristics of the Time, Location, Context (TLC) normalized signal;

accessing an event history of one or more events previously detected at the venue based on the characteristics of other Time, Location, Context (TLC) normalized signals;

deriving an event context from the characteristics of the Time, Location, Context (TLC) normalized signal and the contents of the event history;

submitting the event context to a planning system potentially associated with an actual planned event at the venue;

receiving validating data from the planning system;

validating the possible planned event as the actual planned event from the validating data; and

notifying an entity of the actual planned event, the entity selected from among a person, a business entity, or a governmental entity.

2. The method of claim 1, wherein applying a transform to re-code the source data and reduce the dimensionality of the raw signal comprises applying a transform to re-code the source data and reduce the dimensionality of the raw signal, the raw signal selected from among:

a social post with geographic content, an image from a traffic camera feed, a 911 call, weather data, IoT device data, satellite data, satellite imagery, a sound clip from a listening device, data from air quality sensors, a sound clip from radio communication, crowd sourced traffic information, or crowd sourced road information.

3. The method of claim 1, wherein detecting a possible planned event in an event category comprises classifying the possible planned event in the event category.

4. The method of claim 1, wherein deriving a venue of the possible planned event comprises referring to an event history database.

5. The method of claim 4, wherein referring to an event history database comprises referring to a geo cell database.

6. The method of claim 1, wherein

detecting a possible planned event in an event category based on characteristics of the Time, Location, Context (TLC) normalized signal comprises detecting a possible planned event based on the Context dimension.

7. A method comprising:

normalizing a raw signal into a Time, Location, Context (TLC) normalized signal including applying a transform to re-code source data contained in the raw signal and to reduce the dimensionality of the raw signal into a Time dimension, a Location dimension, and Context dimension

detecting a possible planned event in an event category based on characteristics of the Time, Location, Context (TLC) normalized signal;

deriving a venue of the possible planned event based on characteristics of the Time, Location, Context (TLC) normalized signal;

deriving an event context from the characteristics of the Time, Location, Context (TLC) normalized signal and an event history of one or more events previously detected at the venue;

validating the possible planned event as an actual planned event based on the event context, including;

acquiring first planned event data from a first website, the first planned event data including a first date, a first start time, a first end time, and a first location;

acquiring second planned event data from a second web site, the second planned event data including a second date, a second start time, a second end time, and a second location;

identifying an inconsistency between at least one of;

the first date and the second date, the first start time and the second start time, the first end time and the second end time, or the first location and the second location;

automatically resolving the inconsistency into consistent details of the actual planned event; and

notifying an entity of the actual planned event, the entity selected from among a person, a business entity, or a governmental entity.

8. The method of claim 7, wherein automatically resolving the inconsistency into consistent details of a planned event comprises using machine learning, artificial intelligence, or neural networks to resolve the inconsistency into consistent details.

9. The method of claim 7, wherein automatically resolving the inconsistency into consistent details of a planned event comprises:

identifying a search term in one of the first planned event data or the second planned event data;

referring to a geo cell database to identify a geo cell associated with the search term; and

using other information associated with the geo cell to resolve the inconsistency.

10. The method of claim 9, wherein using other information associated with the geo cell to resolve the inconsistency comprises using the other information associated with the geo cell to resolve an inconsistency between the first location and the second location, including:

querying a venue database with the other information; and

receiving an indication of the venue from the venue database, the venue in a geographic area defined by the geo cell.

11. A computer system comprising:

a processor;

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

ingest a raw signal including a time stamp, an indication of a signal type, an indication of a signal source, and source data;

apply a transform to re-code the source data and reduce the dimensionality of the raw signal into a Time, Location, Context (TLC) normalized signal including a Time dimension, a Location dimension, and Context dimension;

detect a possible planned event in an event category based on characteristics of the Time, Location, Context (TLC) normalized signal;

derive a venue of the possible planned event based on characteristics of the Time, Location, Context (TLC) normalized signal;

access an event history of one or more events previously detected at the venue based on the characteristics of other Time, Location, Context (TLC) normalized signals;

derive an event context from the characteristics of the Time, Location, Context (TLC) normalized signal and the contents of the event history;

submit the event context to a planning system potentially associated with an actual planned event at the venue;

receive validating data from the planning system;

validate the possible planned event as the actual planned event from the validating data; and

notify an entity of the actual planned event, the entity selected from among a person, a business entity, or a governmental entity.

12. The computer system of claim 11, wherein instructions configured to apply a transform to re-code the source data and reduce the dimensionality of the raw signal comprise instructions configured to applying a transform to re-code the source data and reduce the dimensionality of the raw signal, the raw signal selected from among:

a social post, an image, a 911 call, weather data, IoT device data, satellite data, satellite imagery, a sound clip, data from air quality sensors, crowd sourced traffic information, or crowd sourced road information.

13. The computer system of claim 11, wherein instructions configured to detect a possible planned event in an event category comprise instructions configured to classify the possible planned event in the event category.

14. The computer system of claim 11, wherein instructions configured to derive a venue of the possible planned event comprise instructions configured to refer to an event history database.

15. The computer system of claim 14, wherein instructions configured to refer to an event history database comprise instructions configured to refer to a geo cell database.

16. The computer system of claim 11, wherein instructions configured to detect a possible planned event in an event category based on characteristics of the Time, Location, Context (TLC) normalized signal comprise instructions configured to detect a possible planned event based on the Context dimension.