Systems and methods for utilizing a machine learning model to identify public parking spaces and for providing notifications of available public parking spaces

1. A method comprising:

receiving, by a device, geographical data identifying a geographical area in which vehicles are parked in parking spaces;

receiving, by the device and from vehicle devices of the vehicles, first vehicle data identifying engine off conditions, locations during engine off conditions, and durations of the engine off conditions;

dividing, by the device and based on the geographical data, the geographical area into clusters with particular dimensions;

processing, by the device, data identifying the clusters of the geographical area and the first vehicle data, with a machine learning model, to determine parking data identifying public parking spaces in the geographical area;

receiving, by the device and from a set of the vehicle devices associated with vehicles parked in the public parking spaces, second vehicle data identifying engine on conditions and locations during the engine on conditions;

identifying, by the device, available public parking spaces in the geographical area based on the second vehicle data and the parking data; and

performing, by the device, one or more actions based on the data identifying the available public parking spaces.

2. The method of claim 1 , wherein processing the data identifying the clusters of the geographical area and historical vehicle data, with a machine learning model, to determine the parking data comprises:

establishing a threshold time period associated with the durations of the engine off conditions;

establishing a threshold quantity of the engine off conditions;

establishing a threshold quantity of the vehicles associated with the engine off conditions; and

determining the parking data identifying the public parking spaces in the geographical area based on the threshold time period, the threshold quantity of the engine off conditions, and the threshold quantity of the vehicles associated with the engine off conditions.

3. The method of claim 1 , wherein performing the one or more actions comprises:

receiving, from a particular vehicle device of a particular vehicle, a current location of the particular vehicle and a request to locate parking within a region of the geographical area;

identifying one or more of the available public parking spaces based on the data identifying the available public parking spaces, the current location of the particular vehicle, and the request to locate parking; and

providing, to the particular vehicle device, a user interface that includes locations of and directions to the one or more of the available public parking spaces.

4. The method of claim 3 , wherein performing the one or more actions further comprises:

periodically identifying additional available public parking spaces, of the available public parking spaces, based on the data identifying the available public parking spaces, the current location of the particular vehicle, and the request to locate parking,

wherein the additional available public parking spaces are identified until the particular vehicle parks; and

providing, to the particular vehicle device, another user interface that includes locations of and directions to the additional available public parking spaces.

5. The method of claim 3 , wherein performing the one or more actions further comprises:

determining that a particular available public parking space, of the one or more of the available public parking spaces, has become occupied;

modifying the user interface to remove a location of and directions to the particular available public parking space and to generate a modified user interface; and

providing the modified user interface to the particular vehicle device.

6. The method of claim 1 , further comprising:

determining accelerations or movements of the vehicles parked in the public parking spaces,

wherein identifying the available public parking spaces in the geographical area based on the second vehicle data and the parking data comprises:

identifying the available public parking spaces in the geographical area based on determining the accelerations or the movements of the vehicles parked in the public parking spaces.

7. A device, comprising:

one or more processors configured to:

receive geographical data identifying a geographical area in which vehicles are parked in parking spaces;

receive, from vehicle devices of the vehicles, first vehicle data identifying engine off conditions, locations during engine off conditions, and durations of the engine off conditions;

divide, based on the geographical data, the geographical area into clusters with particular dimensions;

process data identifying the clusters of the geographical area and the first vehicle data, with a machine learning model, to determine parking data identifying public parking spaces in the geographical area;

receive, from a set of the vehicle devices associated with vehicles parked in the public parking spaces, second vehicle data identifying engine on conditions and locations during the engine on conditions;

identify available public parking spaces in the geographical area based on the second vehicle data and the parking data;

receive, from a particular vehicle device of a particular vehicle, a current location of the particular vehicle and a request to locate parking within a region of the geographical area;

identify one or more of the available public parking spaces based on the data identifying the available public parking spaces, the current location of the particular vehicle, and the request to locate parking; and

provide, to the particular vehicle device, a user interface that includes locations of and directions to the one or more of the available public parking spaces.

8. The device of claim 7 , wherein the one or more processors are further configured to:

identify a closest available public parking space, of the available public parking spaces and to the particular vehicle, based on the data identifying the available public parking spaces, the current location of the particular vehicle, and the request to locate parking; and

provide, to the particular vehicle device, data identifying the closest available public parking space.

9. The device of claim 7 , wherein the one or more processors are further configured to:

determine that the closest available public parking space has become occupied;

identify a next closest available public parking space, of the available public parking spaces and to the particular vehicle, based on determining that the closest available public parking space has become occupied; and

provide, to the particular vehicle device, data identifying the next closest available public parking space.

10. The device of claim 7 , wherein the one or more processors are further configured to:

receive additional parking data identifying one or more public parking lots;

modify the parking data, based on the additional parking data, to generate modified parking data; and

identify the available public parking spaces in the geographical area based on the second vehicle data and the modified parking data.

11. The device of claim 7 , wherein the one or more processors are further configured to:

reduce the particular dimensions of the clusters of the geographical area,

wherein reducing the particular dimensions increases an accuracy of the parking data identifying public parking spaces in the geographical area relative to the parking data associated with the particular dimensions.

12. The device of claim 7 , wherein the one or more processors, when processing the data identifying the clusters of the geographical area and the first vehicle data, with the machine learning model, to determine the parking data, are to:

periodically process, over a predetermined time period, the data identifying the clusters of the geographical area and the first vehicle data, with the machine learning model, to determine the parking data.

13. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors, cause the one or more processors to:

receive geographical data identifying a geographical area in which vehicles are parked in parking spaces;

receive, from vehicle devices of the vehicles, first vehicle data identifying engine off conditions, locations during engine off conditions, and durations of the engine off conditions;

divide, based on the geographical data, the geographical area into clusters with particular dimensions;

process data identifying the clusters of the geographical area and the first vehicle data, with a machine learning model, to determine parking data identifying public parking spaces in the geographical area;

receive, from a set of the vehicle devices associated with vehicles parked in the public parking spaces, second vehicle data identifying engine on conditions and locations during the engine on conditions;

identify available public parking spaces in the geographical area based on the second vehicle data and the parking data;

store data identifying the available public parking spaces in a data structure; and

perform one or more actions based on the data identifying the available public parking spaces,

wherein the one or more actions include:

receiving, from a particular vehicle device of a particular vehicle, a current location of the particular vehicle and a request to locate parking within a region of the geographical area,

identifying one or more of the available public parking spaces based on the data identifying the available public parking spaces, the current location of the particular vehicle, and the request to locate parking, and

providing, to the particular vehicle device, a user interface that includes locations of and directions to the one or more of the available public parking spaces.

14. The non-transitory computer-readable medium of claim 13 , wherein the one or more instructions, that cause the one or more processors to process the data identifying the clusters of the geographical area and the first vehicle data, with a machine learning model, to determine the parking data, cause the one or more processors to:

establish a threshold time period associated with the durations of the engine off conditions;

establish a threshold quantity of the engine off conditions;

establish a threshold quantity of the vehicles associated with the engine off conditions; and

determine the parking data identifying the public parking spaces in the geographical area based on the threshold time period, the threshold quantity of the engine off conditions, and the threshold quantity of the vehicles associated with the engine off conditions.

15. The non-transitory computer-readable medium of claim 13 , wherein the one or more instructions, that cause the one or more processors to perform the one or more actions, cause the one or more processors to:

modify, over time, representations of the one or more of the available public parking spaces in the user interface to generate a modified user interface; and

provide the modified user interface to the particular vehicle device.

16. The non-transitory computer-readable medium of claim 13 , wherein the one or more instructions, that cause the one or more processors to perform the one or more actions, cause the one or more processors to:

continuously identify additional available public parking spaces, of the available public parking spaces, based on the data identifying the available public parking spaces, the current location of the particular vehicle, and the request to locate parking,

wherein the additional available public parking spaces are identified until the particular vehicle parks; and

provide, to the particular vehicle device, another user interface that includes locations of and directions to the additional available public parking spaces.

17. The non-transitory computer-readable medium of claim 13 , wherein the instructions further comprise:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to:

receive additional parking data identifying one or more public parking lots;

modify the parking data, based on the additional parking data, to generate modified parking data; and

identify the available public parking spaces in the geographical area based on the second vehicle data and the modified parking data.

18. The non-transitory computer-readable medium of claim 13 , wherein the instructions further comprise:

one or more instructions that, when executed by the one or more processors, cause the one or more processors to:

reduce the particular dimensions of the clusters of the geographical area,

wherein reducing the particular dimensions increases an accuracy of the parking data identifying public parking spaces in the geographical area relative to the parking data associated with the particular dimensions.

19. The method of claim 1 , further comprising:

adjusting the particular dimensions of the clusters of the geographical area,

wherein adjusting the particular dimensions increases an accuracy of the parking data identifying public parking spaces in the geographical area relative to the parking data associated with the particular dimensions.

20. The method of claim 1 , wherein the determining parking data identifying public parking spaces in the geographical area comprises determining whether the durations of the engine off conditions satisfy an engine off duration parameter threshold.