CORRECTING INCONSISTENCIES IN SPATIO-TEMPORAL PREDICTION SYSTEM

• US 20150066828A1
• Filed: 08/27/2014
• Published: 03/05/2015
• Est. Priority Date: 08/27/2013
• Status: Abandoned Application

• Current Assignee: Twisted Pair Solutions Inc. (Motorola Solutions, Inc.)
• Original Assignee: Public Engines, Inc. (Motorola Solutions, Inc.)
• Inventors: Vepakomma, Praneeth
• Application Number:
  US14/470,695
• Publication Number:
  US 20150066828A1
• Time in Patent Office: Days
• US Class Current: 706/46
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202

Abstract

An apparatus, method, and computer program product are disclosed for correcting inconsistencies in a spatio-temporal prediction system. A data module receives event-prediction data comprising a plurality of prediction probabilities. The plurality of prediction probabilities includes one or more ordering inconsistencies. A ranking module calculates one or more event-prediction rankings based on the event-prediction data while adjusting for the one or more ordering inconsistencies. A probability-ordering module orders the prediction probabilities based on the one or more event-prediction rankings.

Claims

1. An apparatus comprising:

a data module configured to receive event-prediction data comprising a plurality of prediction probabilities, the plurality of prediction probabilities comprising one or more ordering inconsistencies;

a ranking module configured to calculate one or more event-prediction rankings based on the event-prediction data while adjusting for the one or more ordering inconsistencies; and

a probability-ordering module configured to order the prediction probabilities based on the one or more event-prediction rankings.

2. The apparatus of claim 1, further comprising a map module configured to present a map of an area associated with the event-prediction probabilities.

3. The apparatus of claim 2, wherein the area presented on the map is associated with one or more crimes, the event-prediction probabilities being derived from spatio-temporal data associated with the one or more crimes.

4. The apparatus of claim 1, further comprising an overlay module configured to overlay one or more hotspots on a map, the one or more hotspots indicating an area on the map that has a prediction probability above a predetermined threshold.

5. The apparatus of claim 4, wherein the overlay module further assigns a rank to the one or more hotspots according to the order of the prediction probabilities determined by the probability-ordering module.

6. The apparatus of claim 4, wherein the one or more hotspots are associated with one or more selected crimes, the one or more hotspots representing a likelihood of a near-repeat of a selected crime occurring in an area of the map associated with the hotspot.

7. The apparatus of claim 1, wherein the event-prediction probability data is derived from spatio-temporal data, the spatio-temporal data comprising one or more of a time and a location.

8. The apparatus of claim 7, wherein the spatio-temporal data comprises crime data, the crime data comprising a time of a crime and a location of a crime.

9. The apparatus of claim 1, wherein the plurality of prediction probabilities comprise real numbers that are arranged in a real matrix, the real matrix comprising one of an asymmetric matrix, a symmetric matrix, and a skew symmetric matrix.

10. The apparatus of claim 1, wherein the ranking module calculates the one or more event-prediction rankings using a discrete Helmholtz-Hodge decomposition.

11. A method comprising:

receiving event-prediction data comprising a plurality of prediction probabilities, the plurality of prediction probabilities comprising one or more ordering inconsistencies;

calculating one or more event-prediction rankings based on the event-prediction data while adjusting for the one or more ordering inconsistencies; and

ordering the prediction probabilities based on the one or more event-prediction rankings.

12. The method of claim 11, further comprising presenting a map of an area associated with the event-prediction probabilities.

13. The method of claim 12, wherein the area presented on the map is associated with one or more crimes, the event-prediction probabilities being derived from spatio-temporal data associated with the one or more crimes.

14. The method of claim 11, further comprising overlaying one or more hotspots on a map, the one or more hotspots indicating an area on the map that has a prediction probability above a predetermined threshold.

15. The method of claim 14, further comprising assigning a rank to the one or more hotspots according to the order of the prediction probabilities determined by the probability-ordering module.

16. The method of claim 14, wherein the one or more hotspots are associated with one or more selected crimes, the one or more hotspots representing a likelihood of a near-repeat of a selected crime occurring in an area of the map associated with the hotspot.

17. The method of claim 11, wherein the event-prediction probability data is derived from spatio-temporal data, the spatio-temporal data comprising one or more of a time and a location.

18. The method of claim 17, wherein the spatio-temporal data comprises crime data, the crime data comprising a time of a crime and a location of a crime.

19. The method of claim 11, wherein the plurality of prediction probabilities comprise real numbers that are arranged in a real matrix, the real matrix comprising one of an asymmetric matrix, a symmetric matrix, and a skew symmetric matrix.

20. A program product comprising a computer readable storage medium that stores code executable by a processor, the executable code comprising code to perform:

receiving event-prediction data comprising a plurality of prediction probabilities, the plurality of prediction probabilities comprising one or more ordering inconsistencies;

calculating one or more event-prediction rankings based on the event-prediction data while adjusting for the one or more ordering inconsistencies; and

ordering the prediction probabilities based on the one or more event-prediction rankings.