Stop purpose classification for vehicle fleets

1. A device, comprising:

one or more processors to:

receive location information and work order information associated with a plurality of vehicles;

group the location information into:

engine off information,

idling information, and

journey information;

combine, based on the journey information, the engine off information and the idling information to generate vehicle stop information associated with the plurality of vehicles;

match corresponding work order information with the vehicle stop information to generate matched information;

extract stop-wise features, points of interest features, stop cluster features, and sequential features from the vehicle stop information;

utilize the stop-wise features, the points of interest features, the stop cluster features, and the sequential features with a model to determine work order stops and non-work order stops for the plurality of vehicles,

wherein the stop cluster features are determined based on analyzing radiuses associated with a plurality of vehicle stops to determine a geographic area associated with a particular vehicle stop; and

provide information associated with the work order stops and the non-work order stops for the plurality of vehicles.

2. The device of claim 1 , where:

the location information includes global positioning system (GPS) information associated with the plurality of vehicles, and

the work order information includes information indicating schedules of work tasks associated with the plurality of vehicles over a period of time.

3. The device of claim 1 , where the one or more processors are further to:

determine that a first portion of the location information is associated with when engines of a first one or more of the plurality of vehicles are turned off;

determine that a second portion of the location information is associated with when engines of a second one or more of the plurality of vehicles are turned on, and when the second one or more of the plurality of vehicles are not moving or are moving slowly;

determine that a third portion of the location information is not associated with the first portion of the location information and the second portion of the location information;

identify the first portion of the location information as the engine off information;

identify the second portion of the location information as the idling information; and

identify the third portion of the location information as the journey information.

4. The device of claim 1 , where the one or more processors are further to:

utilize a rule-based clustering technique to group the idling information and the engine off information into stops.

5. The device of claim 1 , where:

the stop-wise features include features associated with vehicle stop durations and a total quantity of location signals associated with each vehicle stop,

the points of interest features include features associated with points of interest in a geographic area surrounding each vehicle stop,

the stop cluster features include features that describe characteristics of vehicle stops surrounding a particular vehicle stop, and

the sequential features include features associated with a sequence of vehicle stops performed prior to and after each vehicle stop.

6. The device of claim 1 , where the model includes a random forest classifier model.

7. The device of claim 1 , where the one or more processors are further to:

train the model, based on the stop-wise features, the points of interest features, the stop cluster features, and the sequential features, to generate a trained model; and

determine the work order stops and the non-work order stops for the plurality of vehicles based on the trained model.

8. 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 location information and work order information associated with a plurality of vehicles;

group the location information into:

engine off information,

idling information, and

journey information;

combine, based on the journey information, the engine off information and the idling information to generate vehicle stop information associated with the plurality of vehicles;

match corresponding work order information with the vehicle stop information to generate matched information;

extract stop-wise features, points of interest features, stop cluster features, and sequential features from the vehicle stop information,

wherein the stop cluster features are determined based on analyzing radiuses associated with a plurality of vehicle stops to determine a geographic area associated with a particular vehicle stop;

utilize the stop-wise features, the points of interest features, the stop cluster features, and the sequential features with a model to determine work order stops and non-work order stops for the plurality of vehicles; and

provide information associated with the work order stops and the non-work order stops for the plurality of vehicles.

9. The non-transitory computer-readable medium of claim 8 , where:

the location information includes global positioning system (GPS) information associated with the plurality of vehicles, and

the work order information includes information indicating schedules of work tasks associated with the plurality of vehicles over a period of time.

10. The non-transitory computer-readable medium of claim 8 , where the instructions further comprise:

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

determine that a first portion of the location information is associated with when engines of a first one or more of the plurality of vehicles are turned off;

determine that a second portion of the location information is associated with when engines of a second one or more of the plurality of vehicles are turned on, and when the second one or more of the plurality of vehicles are not moving or are moving slowly;

determine that a third portion of the location information is not associated with the first portion of the location information and the second portion of the location information;

identify the first portion of the location information as the engine off information;

identify the second portion of the location information as the idling information; and

identify the third portion of the location information as the journey information.

11. The non-transitory computer-readable medium of claim 8 , where the instructions further comprise:

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

utilize a rule-based clustering technique to group the engine off information and the idling information into stops.

12. The non-transitory computer-readable medium of claim 8 , where:

the stop-wise features include features associated with vehicle stop durations and a total quantity of location signals associated with each vehicle stop,

the points of interest features include features associated with points of interest in a geographic area surrounding each vehicle stop,

the stop cluster features include features that describe characteristics of vehicle stops surrounding a particular vehicle stop, and

the sequential features include features associated with a sequence of vehicle stops performed prior to and after each vehicle stop.

13. The non-transitory computer-readable medium of claim 8 , where the instructions further comprise:

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

train the model, based on the stop-wise features, the points of interest features, the stop cluster features, and the sequential features, to generate a trained model; and

determine the work order stops and the non-work order stops for the plurality of vehicles based on the trained model.

14. The non-transitory computer-readable medium of claim 8 , where the instructions further comprise:

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

provide, for display, a user interface that includes the information associated with the work order stops and the non-work order stops.

15. A method, comprising:

receiving, by a device, location information and work order information associated with a plurality of vehicles;

grouping, by the device, the location information into engine off information, idling information, and journey information;

combining, by the device and based on the journey information, the engine off information and the idling information to generate vehicle stop information associated with the plurality of vehicles;

matching, by the device, corresponding work order information with the vehicle stop information to generate matched information;

extracting, by the device, stop-wise features, points of interest features, stop cluster features, and sequential features from the vehicle stop information,

wherein the stop cluster features are determined based on analyzing radiuses associated with a plurality of vehicle stops to determine a geographic area associated with a particular vehicle stop;

utilizing, by the device, the stop-wise features, the points of interest features, the stop cluster features, and the sequential features with a model to determine work order stops and non-work order stops for the plurality of vehicles; and

providing, by the device, information associated with the work order stops and the non-work order stops for the plurality of vehicles.

16. The method of claim 15 , where:

the location information includes global positioning system (GPS) information associated with the plurality of vehicles, and

the work order information includes information indicating schedules of work tasks associated with the plurality of vehicles over a period of time.

17. The method of claim 15 , where:

the engine off information includes a first portion of the location information that is associated with when engines of a first one or more of the plurality of vehicles are turned off;

the idling information includes a second portion of the location information that is associated with when engines of a second one or more of the plurality of vehicles are turned on, and when the second one or more of the plurality of vehicles are not moving or are moving slowly; and

the journey information includes a third portion of the location information that is not associated with the first portion of the location information and the second portion of the location information.

18. The method of claim 15 , further comprising:

utilizing a rule-based clustering technique to group the engine off information and the idling information into stops.

19. The method of claim 15 , where the model includes a random forest classifier model.

20. The method of claim 15 , further comprising:

training the model, based on the stop-wise features, the points of interest features, the stop cluster features, and the sequential features, to generate a trained model; and

determining the work order stops and the non-work order stops for the plurality of vehicles based on the trained model.