PREDICTIVE ANALYTICS FOR EMERGENCY DETECTION AND RESPONSE MANAGEMENT

• US 20180053401A1
• Filed: 08/21/2017
• Published: 02/22/2018
• Est. Priority Date: 08/22/2016
• Status: Active Grant

• Current Assignee: Rapidsos, Inc.
• Original Assignee: Rapidsos, Inc.
• Inventors: Martin, Michael John, Horelik, Nicholas Edward, Hornbaker, II, Charles LeForrest, Sancier-Barbosa, Flavia Cabral, Mehta, Anil
• Granted Patent: US 10,861,320 B2
• Time in Patent Office: Days
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G08B 17/00 Fire alarms; Alarms responsive to explosion
• CPC Class Codes: G08B 21/10 responsive to calamitous events, e.g. tornados or earthquakes
• CPC Class Codes: G08B 27/005 with transmission via computer network
• CPC Class Codes: G08B 29/188 Data fusion; cooperative systems, e.g. voting among different detectors
• CPC Class Codes: G08B 31/00 Predictive alarm systems characterised by extrapolation or other computation using updated historic data
• CPC Class Codes: H04L 12/1895 for short real-time information, e.g. alarms, notifications, alerts, updates
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
• CPC Class Codes: H04L 67/04 specially adapted for terminals or networks with limited capabilities; specially adapted for terminal portability
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• 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: H04M 1/72421 with automatic activation of emergency service functions, e.g. upon sensing an alarm
• CPC Class Codes: H04M 11/04 with alarm systems, e.g. fire, police or burglar alarm systems
• CPC Class Codes: H04M 2250/12 including a sensor for measuring a physical value, e.g. temperature or motion
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/14 Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]
• 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

Disclosed are systems, methods, and media capable of generating emergency predictions. The systems, methods, and media generate spatiotemporal emergency communication predictions, carry out data augmentation, detect emergency anomalies, optimize emergency resource allocation, or any combination thereof.

Claims

1. A method of creating a prediction model for generating at least one spatiotemporal emergency prediction, the method comprising:

a) obtaining, by an emergency prediction system (EPS), emergency data comprising emergency type, emergency location, and emergency time for a plurality of emergency communications;

b) augmenting, by the emergency prediction system, the emergency data with additional data associated with the plurality of emergency communications based on at least one of emergency time, emergency location, and calling identity;

c) generating, by the emergency prediction system, at least one prediction model for making at least one spatiotemporal emergency prediction using the emergency data; and

d) using, by the emergency prediction system, the at least one prediction model to generate at least one spatiotemporal emergency prediction corresponding to a defined emergency type, a defined geographic area, and a defined time period.

2. The method of claim 1, wherein the at least one prediction model is generated using a point cloud comprising points sampled from at least one of current emergency data, proprietary emergency data, and a proprietary data stream.

3. The method of claim 1, wherein augmenting the emergency data with additional data in (b) comprises obtaining additional data, matching at least a subset of the additional data with at least a subset of the emergency data, and combining information from the at least a subset of the additional data and the at least a subset of the emergency data to form augmented data.

4. The method of claim 1, further comprising providing, by the emergency prediction system, the at least one spatiotemporal emergency prediction to an emergency dispatch center serving the defined geographic area.

5. The method of claim 4, wherein providing the spatiotemporal emergency prediction comprises displaying a set of predicted kernel density estimates on a digital map.

6. The method of claim 1, wherein the spatiotemporal emergency prediction is an aggregation of a plurality of spatiotemporal emergency predictions generated for subsets of the defined geographic area.

7. The method of claim 1, further comprising using an allocation algorithm to generate a recommendation for optimal allocation of local emergency resources based on the at least one spatiotemporal emergency prediction.

8. An emergency prediction system (EPS) comprising at least one processor, an operating system configured to perform executable instructions, a memory, and a computer program including instructions executable by the at least one processor to create an application comprising:

a) a software module obtaining emergency data comprising emergency type, emergency location, and emergency time for a plurality of emergency communications;

b) a software module augmenting the emergency data with additional data associated with the plurality of emergency communications based on at least one of emergency time, emergency location, and calling identity;

c) a software module generating at least one prediction model for making at least one spatiotemporal emergency prediction using the emergency data; and

d) a software module using the at least one prediction model to generate at least one spatiotemporal emergency prediction corresponding to a defined emergency type, a defined geographic area, and a defined time period.

9. The emergency prediction system of claim 8, wherein the at least one prediction model is generated using a point cloud comprising points sampled from at least one of current emergency data, proprietary emergency data, and a proprietary data stream.

10. The emergency prediction system of claim 8, wherein augmenting the emergency data with additional data in (b) comprises obtaining additional data, matching at least a subset of the additional data with at least a subset of the emergency data, and combining information from the at least a subset of the additional data and the at least a subset of the emergency data to form augmented data.

11. The emergency prediction system of claim 8, wherein the emergency prediction system provides the at least one spatiotemporal emergency prediction to an emergency dispatch center serving the defined geographic area.

12. The emergency prediction system of claim 8, further comprising a software module using an allocation algorithm to generate a recommendation for optimal allocation of local emergency resources based on the at least one spatiotemporal emergency prediction.

13. A method for detecting an emergency anomaly, comprising:

a) obtaining, by an emergency prediction system, emergency data for current emergency communications, said emergency data comprising emergency time and emergency location;

b) providing, by the emergency prediction system, an emergency anomaly detection algorithm for monitoring the emergency communications to identify the emergency anomaly; and

c) executing, by the emergency prediction system, the emergency anomaly detection algorithm to identify the emergency anomaly based on the emergency data, said emergency anomaly comprising a cluster of emergency communications.

14. The method of claim 13, further comprising using, by the emergency prediction system, a multi-class classifier to predict at least one of emergency type and emergency priority for the cluster of emergency communications.

15. The method of claim 13, wherein the emergency data comprises labeled incident data, unlabeled incident data, augmented incident data, or any combination thereof.

16. The method of claim 13, wherein the emergency anomaly is identified in real-time or near real-time.

17. The method of claim 13, wherein the emergency anomaly detection algorithm uses a cluster detection model to identify the emergency anomaly.

18. The method of claim 13, wherein the cluster comprises emergency communications that correspond to a defined geographic area, a defined time period, and a defined emergency type.

19. The method of claim 13, further comprising providing, by the emergency prediction system, the emergency anomaly to an emergency dispatch center.

20. The method of claim 19, wherein providing the emergency anomaly comprises displaying the cluster of emergency communications on a digital map.