Crime risk forecasting

• US 9,836,694 B2
• Filed: 09/02/2015
• Issued: 12/05/2017
• Est. Priority Date: 06/30/2014
• Status: Active Grant

• Current Assignee: Palantir Technologies Incorporated
• Original Assignee: Palantir Technologies Incorporated
• Inventors: Robertson, Duncan, Sparrow, Alexander, Lewin, Mike, Von Brentano, Meline, Elkherj, Matthew, Cosman, Rafael
• Primary Examiner(s): Hill, Stanley K
• Assistant Examiner(s): Chubb, Mikayla
• Application Number:
  US14/843,734
• Publication Number:
  US 20150379413A1
• Time in Patent Office: 825 Days
• Field of Search: None
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/20 Ensemble learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• 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
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 50/26 Government or public services business processes related to the transportation industry G06Q50/40
• CPC Class Codes: G06Q 50/265 Personal security, identity or safety

Abstract

A computer-based crime risk forecasting system and corresponding method are provided for generating crime risk forecasts and conveying the forecasts to a user. With the conveyed forecasts, the user can more effectively gauge both the level of increased crime threat and its potential duration. The user can then leverage the information conveyed by the forecasts to take a more proactive approach to law enforcement in the affected areas during the period of increased crime threat.

Claims

1. A system comprising:

one or more hardware processors;

storage media; and

one or more computer programs stored in the storage media for execution by the one or more hardware processors, the one or more computer programs comprising;

instructions for generating a crime risk forecast based at least on historical crime incidents;

wherein the generated crime risk forecast is for a particular target geographic area, a particular future time window, and a particular crime type;

instructions for generating a graphical user interface overlay to an interactive geospatial basemap generated by a geospatial application;

wherein the overlay visually indicates the particular target geographic area on the interactive geospatial basemap;

wherein the overlay visually indicates the particular future time window;

wherein the overlay visually indicates the particular crime type, and

wherein the instructions for generating the crime risk forecast comprise instructions for generating the crime risk forecast based, at least in part, on at least one of;

(a) a level of historical law enforcement patrol activity in the particular target geographic area,

(b) custody information reflecting apprehension one or more persons known to have committed one or more of the historical crime incidents in the particular target geographic area,

(c) custody information reflecting release from custody of one or more persons known to have committed one or more of the historical crime incidents in the particular target geographic area, or

(d) any combination of (a), (b), or (c).

2. The system of claim 1, the one or more computer programs further comprising:

instructions for generating a crime risk rating for the particular target geographic area, the particular future time window, and the particular crime type; and

wherein the overlay visually indicates the crime risk rating.

3. The system of claim 1, wherein the particular future time window corresponds to a particular future law enforcement patrol shift;

and wherein the overlay visually indicates the particular future law enforcement patrol shift.

4. The system of claim 1, wherein the instructions for generating the crime risk forecast comprise instructions for generating the crime risk forecast based at least on a number of historical crime incidents that occurred in a geographic area neighboring the particular target geographic area.

5. The system of claim 1, wherein the instructions for generating the crime risk forecast comprise instructions for generating the crime risk forecast based at least on a level of historical law enforcement patrol activity in the particular target geographic area.

6. The system of claim 1, wherein the instructions for generating the crime risk forecast comprise instructions for generating the crime risk forecast based at least on custody information reflecting apprehension one or more persons known to have committed one or more of the historical crime incidents in the particular target geographic area.

7. The system of claim 1, wherein the instructions for generating the crime risk forecast comprise instructions for generating the crime risk forecast based at least on custody information reflecting release from custody of one or more persons known to have committed one or more of the historical crime incidents in the particular target geographic area.

8. The system of claim 1, wherein the instructions for generating the crime risk forecast comprise:

instructions for generating a first crime risk value for the particular target geographic area, the particular future time window, and the particular crime type based at least on a weighted sum of a plurality of historical crime incidents, of the historical crime incidents, within a space threshold and a time threshold;

instructions for generating a second crime risk value for the particular target geographic area, the particular future time window, and the particular crime type based at least on a sum of a plurality of historical crime incidents, of the historical crime incidents, that occurred in the particular target geographic area; and

instructions for generating a third crime risk value for the particular target geographic area, the particular future time window, and the particular crime type based at least on a machine learning algorithm that uses at least the first crime risk value and the second crime risk value as machine learning features.

9. The system of claim 1, wherein the instructions for generating the crime risk forecast comprise instructions for generating the crime risk forecast based at least on computer-aided dispatch data reflecting crime type, crime date, and crime location of one or more of the historical crime incidents.

10. The system of claim 1, wherein the instructions for generating the graphical user interface overlay to the interactive geospatial basemap comprise instructions for generating the graphical user interface overlay at a web browser.

11. A method comprising:

at one or more computing devices comprising one or more hardware processors and memory storing one or more computer programs executed by the one or more hardware processors to perform the method, performing the operations of;

generating a crime risk forecast based at least on historical crime incidents;

wherein the generated crime risk forecast is for a particular target geographic area, a particular future time window, and a particular crime type;

generating a graphical user interface overlay to an interactive geospatial basemap generated by a geospatial application;

wherein the overlay visually indicates the particular target geographic area on the interactive geospatial basemap;

wherein the overlay visually indicates the particular future time window; and

wherein the overlay visually indicates the particular crime type; and

wherein the instructions for generating the crime risk forecast comprise instructions for generating the crime risk forecast based, at least in part, on at least one of;

(a) a level of historical law enforcement patrol activity in the particular target geographic area,

(b) custody information reflecting apprehension one or more persons known to have committed one or more of the historical crime incidents in the particular target geographic area,

(c) custody information reflecting release from custody of one or more persons known to have committed one or more of the historical crime incidents in the particular target geographic area, or

(d) any combination of (a), (b), or (c).

12. The method of claim 11, further performing the operation of:

generating a crime risk rating for the particular target geographic area, the particular future time window, and the particular crime type; and

wherein the overlay visually indicates the crime risk rating.

13. The method of claim 11, wherein the particular future time window corresponds to a particular future law enforcement patrol shift;

and wherein the overlay visually indicates the particular future law enforcement patrol shift.

14. The method of claim 11, wherein the operation of generating the crime risk forecast comprises the operation of generating the crime risk forecast based at least on a number of historical crime incidents that occurred in a geographic area neighboring the particular target geographic area.

15. The method of claim 11, wherein the operation of generating the crime risk forecast comprises the operation of generating the crime risk forecast based at least on a level of historical law enforcement patrol activity in the particular target geographic area.

16. The method of claim 11, wherein the operation of generating the crime risk forecast comprises the operation of generating the crime risk forecast based at least on custody information reflecting apprehension one or more persons known to have committed one or more of the historical crime incidents in the particular target geographic area.

17. The method of claim 11, wherein the operation of generating the crime risk forecast comprises the operation of generating the crime risk forecast based at least on custody information reflecting release from custody of one or more persons known to have committed one or more of the historical crime incidents in the particular target geographic area.

18. The method of claim 11, wherein the operation of generating the crime risk forecast comprises the operations of:

generating a first crime risk value for the particular target geographic area, the particular future time window, and the particular crime type based at least on a weighted sum of a plurality of historical crime incidents, of the historical crime incidents, within a space threshold and a time threshold;

generating a second crime risk value for the particular target geographic area, the particular future time window, and the particular crime type based at least on a sum of a plurality of historical crime incidents, of the historical crime incidents, that occurred in the particular target geographic area; and

generating a third crime risk value for the particular target geographic area, the particular future time window, and the particular crime type based at least on a machine learning algorithm that uses at least the first crime risk value and the second crime risk value as machine learning features.

19. The method of claim 11, wherein the operation of generating the crime risk forecast comprises the operation of generating the crime risk forecast based at least on computer-aided dispatch data reflecting crime type, crime date, and crime location of one or more of the historical crime incidents.

20. The method of claim 11, wherein the operation of generating the graphical user interface overlay to the interactive geospatial basemap comprises the operation of generating the graphical user interface overlay at a web browser.