Predicting parking availability

• US 8,484,151 B1
• Filed: 12/29/2010
• Issued: 07/09/2013
• Est. Priority Date: 12/29/2010
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Lookingbill, Andrew
• Primary Examiner(s): Gaffin, Jeffrey A
• Assistant Examiner(s): Chubb, Mikayla
• Application Number:
  US12/981,278
• Time in Patent Office: 923 Days
• Field of Search: None
• US Class Current: 706/46
• CPC Class Codes: G01C 21/3685 the POI's being parking facilities
• CPC Class Codes: G06N 20/00 Machine learning
• 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: G08G 1/012 from other sources than vehicle or roadside beacons, e.g. mobile networks
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/0141 for traffic information dissemination
• CPC Class Codes: G08G 1/144 on portable or mobile units, e.g. personal digital assistant [PDA]
• CPC Class Codes: G08G 1/147 where the parking area is within an open public zone, e.g. city centre

Abstract

The parking availability for a geographic area is predicted using a parking availability model. The geographic population density for the geographic area is first predicted. The predicted geographic population density is then applied to the parking availability model to produce a prediction of the parking availability for the geographic area. The parking availability model comprises a function that relates predicted geographic population densities with parking availabilities for a geographic area. The predicted parking availability for the geographic area is stored in a computer-readable storage medium. The parking availability predictions may be displayed as a layer within a map, and may be produced for a specifically requested geographic area, or a general geographic area.

Claims

1. A method of predicting parking availability for a geographic area, comprising:

defining a Markov Random Field (MRF) model for estimating a number of mobile devices used within the geographic area;

applying current data describing a number of mobile devices currently observed within the geographic area and historical data describing a number of mobile devices historically observed within the geographic area to the MRF model to produce an estimate of a number of mobile devices currently being used within the geographic area;

predicting a geographic population density for the geographic area responsive to the estimated number of mobile devices currently being used within the geographic area;

applying the predicted geographic population density to a parking availability model to produce a prediction of the parking availability for the geographic area, wherein the parking availability model comprises a function relating predicted geographic population density for the geographic area to predicted parking availability for the geographic area; and

storing the predicted parking availability for the geographic area in a computer-readable storage medium.

2. The method of claim 1, further comprising:

observing actual parking availability within the geographic area at a given time; and

correlating the observed actual parking availability within the geographic area at the given time with a predicted geographic population density for the geographic area at the given time to derive the function relating predicted geographic population density to predicted parking availability for the geographic area.

3. The method of claim 2, wherein the observing and correlating are performed for a plurality of geographic areas to derive a plurality of functions relating predicted geographic population density to predicted parking availability for the plurality of geographic areas.

4. The method of claim 2, wherein the actual parking availability within the geographic area is observed at a plurality of different times of day to produce training data and wherein the correlating correlates the training data with predicted geographic population density estimates for the geographic area at the plurality of different times of day to derive a plurality of functions relating predicted geographic population density to predicted parking availability for the geographic area at the plurality of different times of day.

5. The method of claim 2, wherein the actual parking availability within the geographic area is observed at a plurality of different times of day to produce training data and wherein the correlating correlates the training data with predicted geographic population density estimates for the geographic area at the plurality of different times of day to derive a single function relating predicted geographic population density to predicted parking availability for the geographic area at the plurality of different times of day.

6. The method of claim 2, wherein the actual parking availability within the geographic area is observed on a plurality of different days to produce training data and wherein the correlating correlates the training data with predicted geographic population density estimates for the geographic area on the plurality of different dates to produce a function relating predicted geographic population density to predicted parking availability for the geographic area on the plurality of different days.

7. The method of claim 1, further comprising:

classifying the geographic area as a type of geographic area selected from among a plurality of different types of geographic areas;

wherein the function relates predicted geographic population density to predicted parking availability for the classification type of the geographic area.

8. The method of claim 1, for comprising:

receiving a request for predicted parking availability for the geographic area from a mobile device; and

providing the predicted parking availability for the geographic area to the mobile device responsive to receiving the request.

9. The method of claim 8, wherein providing the predicted parking availability comprises:

providing a map of the geographic area, wherein the map includes a layer graphically illustrating the predicted parking availability for the geographic area.

10. A computer for predicting parking availability for a geographic area, comprising:

a non-transitory computer-readable storage medium storing executable computer program instructions comprising instructions for;

defining a Markov Random Field (MRF) model for estimating a number of mobile devices used within the geographic area;

applying current data describing a number of mobile devices currently observed within the geographic area and historical data describing a number of mobile devices historically observed within the geographic area to the MRF model to produce an estimate of a number of mobile devices currently being used within the geographic area;

predicting a geographic population density for the geographic area responsive to the estimated number of mobile devices currently being used within the geographic area;

applying the predicted geographic population density to a parking availability model to produce a prediction of the parking availability for the geographic area, wherein the parking availability model comprises a function relating predicted geographic population density for the geographic area to predicted parking availability for the geographic area; and

storing the predicted parking availability for the geographic area in a computer-readable storage medium; and

a processor for executing the computer program instructions.

11. The computer of claim 10, further comprising instructions for:

observing actual parking availability within the geographic area at a given time; and

correlating the observed actual parking availability within the geographic area at the given time with a predicted geographic population density for the geographic area at the given time to derive the function relating predicted geographic population density to predicted parking availability for the geographic area.

12. The computer of claim 10, further comprising instructions for:

classifying the geographic area as a type of geographic area selected from among a plurality of different types of geographic areas;

wherein the function relates predicted geographic population density to predicted parking availability for the classification type of the geographic area.

13. The computer of claim 10, further comprising instructions for:

receiving a request for predicted parking availability for the geographic area from a mobile device; and

providing the predicted parking availability for the geographic area to the mobile device responsive to receiving the request.

14. The computer of claim 13, wherein providing the predicted parking availability comprises:

providing a map of the geographic area, wherein the map includes a layer graphically illustrating the predicted parking availability for the geographic area.

15. A non-transitory computer-readable storage medium storing executable computer program instructions for predicting parking availability, the instructions comprising instructions for:

defining a Markov Random Field (MRF) model for estimating a number of mobile devices used within the geographic area;

applying current data describing a number of mobile devices currently observed within the geographic area and historical data describing a number of mobile devices historically observed within the geographic area to the MRF model to produce an estimate of a number of mobile devices currently being used within the geographic area;

predicting a geographic population density for the geographic area responsive to the estimated number of mobile devices currently being used within the geographic area;

applying the predicted geographic population density to a parking availability model to produce a prediction of the parking availability for the geographic area, wherein the parking availability model comprises a function relating predicted geographic population density for the geographic area to predicted parking availability for the geographic area; and

storing the predicted parking availability for the geographic area in a computer-readable storage medium.

16. The non-transitory computer-readable storage medium of claim 15, further comprising instructions for:

observing actual parking availability within the geographic area at a given time; and

correlating the observed actual parking availability within the geographic area at the given time with a predicted geographic population density for the geographic area at the given time to derive the function relating predicted geographic population density to predicted parking availability for the geographic area.

17. The non-transitory computer-readable storage medium of claim 15, further comprising instructions for:

classifying the geographic area as a type of geographic area selected from among a plurality of different types of geographic areas;

wherein the function relates predicted geographic population density to predicted parking availability for the classification type of the geographic area.

18. The non-transitory computer-readable storage medium of claim 15, further comprising instructions for:

receiving a request for predicted parking availability for the geographic area from a mobile device; and

providing the predicted parking availability for the geographic area to the mobile device responsive to receiving the request.

19. The non-transitory computer-readable storage medium of claim 18, wherein providing the predicted parking availability comprises:

providing a map of the geographic area, wherein the map includes a layer graphically illustrating the predicted parking availability for the geographic area.