Predicting parking vacancies based on activity codes

• US 10,339,808 B2
• Filed: 04/03/2017
• Issued: 07/02/2019
• Est. Priority Date: 04/03/2017
• Status: Active Grant

• Current Assignee: HERE Global B.V. (Nokia Corporation)
• Original Assignee: HERE Global B.V. (Nokia Corporation)
• Inventors: Linder, Eric
• Primary Examiner(s): Nguyen, Phung
• Application Number:
  US15/477,354
• Publication Number:
  US 20180286238A1
• Time in Patent Office: 820 Days
• Field of Search: 340932, 3409322, 340988, 3409951
• 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 50/40 Business processes related to the transportation industry shipping G06Q10/083
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0133 for classifying traffic situation
• CPC Class Codes: G08G 1/0141 for traffic information dissemination
• CPC Class Codes: G08G 1/141 with means giving the indication of available parking spaces
• CPC Class Codes: G08G 1/143 inside the vehicles
• CPC Class Codes: G08G 1/147 where the parking area is within an open public zone, e.g. city centre

Abstract

System and methods are provided for predicting occupancy of a parking area. A request is received for data relating to occupancy of the parking area. One or more entities within a first predefined distance of the first parking area are identified. Activity classification codes for each of the one or more entities are identified. A predicted occupancy for the parking area is calculated as a function of the activity classification codes. The predicted occupancy for the parking area is transmitted.

Claims

1. A method for predicting occupancy of a parking area, the method comprising:

receiving, by a processor, a request for data relating to occupancy of the parking area;

identifying, by the processor, one or more first entities within a first predefined distance of the parking area;

receiving, by the processor, at least one activity classification code for each of the one or more first entities, wherein the at least one activity classification code describes a type of economic activity by each of the one or more first entities;

calculating, by the processor, a first predicted occupancy for the parking area as a function of the activity classification codes without sensor data or real time observation data; and

transmitting, by the processor, the first predicted occupancy for the parking area.

2. The method of claim 1, wherein at least one of the activity classification codes describe a first economic activity and a second economic activity for at least one of the first entities.

3. The method of claim 1, wherein the activity classification codes further describe a level of revenue for the one or more first entities.

4. The method of claim 1, wherein calculating the first predicted occupancy comprises:

comparing, by the processor, the activity classification codes to a plurality of patterns identified between a plurality of activity classification codes and historical occupancy data for a plurality of parking areas; and

calculating, by the processor, the predicted occupancy of the parking area based on the comparison.

5. The method of claim 1, wherein the predicted occupancy represents whether the parking area is over or under 50% full.

6. The method of claim 1, wherein the parking area is a first parking area, the method further comprising:

identifying, by the processor, a second parking area in the vicinity of the first parking area;

identifying, by the processor, one or more second entities within a second predefined distance of the second parking area;

receiving, by the processor, at least one activity classification code for each of the one or more second entities;

generating, by the processor, a second predicted occupancy for the second parking area as a function of the activity classifications for the one or more second entities; and

transmitting, by the processor, a location of the second parking area when the second predicted occupancy is lower than the first predicted occupancy.

7. The method of claim 1, wherein the first predicted occupancy is a prediction of whether there is at least one open parking spot in the parking area.

8. The method of claim 1, wherein the predefined distance is based on a walking distance from the parking area.

9. An apparatus for generating a model for predicting occupancy for parking, the apparatus comprising:

at least one processor; and

at least one memory including computer program code for one or more programs;

the at least one memory configured to store the computer program code configured to, with the at least one processor, cause the apparatus to at least perform;

store historical data relating to an occupancy level for a plurality of parking areas;

identify a plurality of economic entities within a predefined distance of each of the plurality of parking areas;

wherein each economic entity of the plurality of economic entities includes an economic activity code stored in the memory; and

identify one or more relationships between the historical data and the economic activity codes for each of the plurality of parking areas;

wherein an occupancy prediction for a requested parking area is based on one or more economic entities within the predefined distance of the requested parking area, economic activity codes of the one or more economic entities, and the one or more relationships.

10. The apparatus of claim 9, wherein the at least one memory and computer program code are configured to cause the apparatus to further perform:

transmit the occupancy prediction for the requested parking area to a navigation device.

11. The apparatus of claim 9, wherein the economic classifications include a first economic activity and a second economic activity for at least one of the economic entities.

12. The apparatus of claim 9, wherein the economic classifications describe a type of economic activity by the economic entities.

13. The apparatus of claim 9, wherein the at least one memory and computer program code are configured to cause the apparatus to further perform:

reduce a number of economic activity codes for each of the plurality of parking areas using principle component analysis;

wherein the one or more relationships are based on the historical data and the reduced economic activity codes.

14. The apparatus of claim 9, wherein the one or more relationships are stored in a parking prediction model.

15. The apparatus of claim 9, wherein the one or more relationships are identified through machine learning classification.

16. The apparatus of claim 9, wherein the historical data comprises an actual observation of whether a parking area is more than half full for a specified time period.

17. A non-transitory computer readable medium including instructions that when executed are operable to:

receive a request for map data relating to a destination;

identify predicted parking occupancy data for one or more parking areas within a distance of the destination;

wherein the predicted parking occupancy data is calculated by a parking occupancy model generated from economic activity classifications of one or more entities within a predefined distance of each of the one or more parking areas without real time sensor data or real time observations; and

render a geographic map including a representation of a predicted parking occupancy for at least one parking area of the one or more parking areas based on the identified predicted parking occupancy data.

18. The non-transitory computer readable medium of claim 17, wherein the geographic map is rendered using different visual effects for different levels of predicted occupancy for the at least one parking area.

19. The non-transitory computer readable medium of claim 17, wherein the instructions that when executed are further operable to:

select a parking area from the at least one parking areas based on user preferences; and

generate a route from a starting point to the selected parking area.