Systems and methods for identifying distracted driving events using unsupervised clustering
A distracted driving analysis system for identifying distracted driving events is provided. The system includes a processor in communication with a memory device programmed to: (i) receive driving event records including phone usage by a user that occurred within a time period of a driving event, (ii) divide the driving event records into at least two clusters based at least in part upon common features of one or more driving event records of the plurality of driving event records by processing the driving event records using an unsupervised machine learning algorithm, (iii) generate a trained model based at least in part upon the at least two clusters including cluster labels, (iv) process a new driving event using the trained model, (v) assign the new driving event to one of the at least two clusters using the trained model, and (vi) based at least in part upon the cluster labels for the assigned cluster, determine whether the new driving event is an actual distracted driving event or a passenger event.
1. A distracted driving analysis system for identifying distracted driving events, the distracted driving analysis system comprising one or more processors, the one or more processors are programmed to:
process a new driving event using a trained model, wherein:
the training model is generated based at least in part on a plurality of driving event records;
the plurality of driving event records is divided into at least two clusters based upon one or more common features of each driving event record by processing the plurality of driving event records using an unsupervised machine learning algorithm; and
each cluster of the at least two clusters includes a corresponding cluster label;
assign the new driving event to one cluster of the at least two clusters using the trained model; and
based upon a cluster label corresponding to the one assigned cluster of the at least two clusters, determine whether the new driving event is an actual distracted driving event.
2. The system of claim 1 , wherein the one assigned cluster of the at least two clusters includes a driving event record indicating a correlation between a sudden braking event and a phone usage.
3. The system of claim 1 , wherein the one cluster of the at least two clusters includes a driving event record indicating a correlation between an acceleration event and a phone usage.
4. The system of claim 1 , wherein the one or more processors are further programmed to:
receive one or more feature inputs from a user computer device, wherein the one or more feature inputs indicate the one or more common features of the plurality of driving event records that should be analyzed in order to categorize and label the driving event records;
display information related to the at least two clusters to a user through the user computer device; and
receive one or more cluster labels from the user computer device, the one or more cluster labels indicating whether the driving event records in each cluster represent actual distracted driving events or passenger events.
5. The system of claim 1 , wherein the one or more processors are further programmed to:
assign a category to the new driving event as an actual distracted driving event or a passenger event; and
determine a confidence level to the category assigned to the new driving event.
6. The system of claim 5 , wherein the one or more processors are further programmed to generate a driver profile for the user, wherein the driver profile includes the categorized new driving event.
7. The system of claim 6 , wherein the one or more processors are further programmed to:
calculate a user safety score based upon the categorized new driving event; and
include the user safety score in the driver profile.
8. The system of claim 7 , wherein the one or more processors are further programmed to generate an insurance policy based upon the driver profile.
9. A computer-implemented method for identifying distracted driving events using a distracted driving analysis system including one or more processors in communication with at least one memory device, the method comprising:
processing a new driving event using the trained model, wherein:
the training model is generated based at least in part on a plurality of driving event records;
the plurality of driving event records is divided into at least two clusters based upon one or more common features of each driving event record by processing the plurality of driving event records using an unsupervised machine learning algorithm; and
each cluster of the at least two clusters includes a corresponding cluster label;
assigning the new driving event to one cluster of the at least two clusters using the trained model; and
based upon a cluster label corresponding to the one assigned cluster of the at least two clusters, determining whether the new driving event is an actual distracted driving event.
10. The computer-implemented method of claim 9 , wherein the one assigned cluster of the at least two clusters includes a driving event record indicating a correlation between a sudden braking event and a phone usage.
11. The computer-implemented method of claim 9 , wherein the one assigned cluster of the at least two clusters includes a driving event record indicating a correlation between an acceleration event and a phone usage.
12. The computer-implemented method of claim 9 further comprising:
receiving one or more feature inputs from a user computer device, wherein the feature inputs indicate the one or more common features of the plurality of driving event records that should be analyzed in order to categorize and label the driving event records;
displaying information related to the at least two clusters to a user through the user computer device; and
receiving one or more cluster labels from the user computer device, the one or more cluster labels indicating whether the driving event records in each cluster represent actual distracted driving events or passenger events.
13. The computer-implemented method of claim 9 further comprising:
assigning a category to the new driving event as an actual distracted driving event or a passenger event;
determining a confidence level to the category assigned to the new driving event.
14. The computer-implemented method of claim 13 further comprising generating a driver profile for the user, wherein the driver profile includes the categorized new driving event.
15. The computer-implemented method of claim 14 further comprising:
calculating a user safety score based upon the categorized new driving event; and
including the user safety score in the driver profile.
16. A non-transitory computer-readable storage medium having computer-executable instructions embodied thereon, wherein when executed by a distracted driving analysis system including one or more processors in communication with at least one memory device, the computer-executable instructions cause the one or more processors to:
process a new driving event using a trained model, wherein:
the training model is generated based at least in part on a plurality of driving event records;
the plurality of driving event records is divided into at least two clusters based upon one or more common features of each driving event record by processing the plurality of driving event records using an unsupervised machine learning algorithm; and
each cluster of the at least two clusters includes a corresponding cluster label;
assign the new driving event to one cluster of the at least two clusters using the trained model; and
based upon a cluster label corresponding the one assigned cluster of the at least two cluster, determine whether the new driving event is an actual distracted driving event.
17. The non-transitory computer-readable storage medium of claim 16 , wherein the one cluster of the at least two clusters includes a driving event record indicating a correlation between a sudden braking event and a phone usage.
18. The non-transitory computer-readable storage medium of claim 16 , wherein the one cluster of the at least two clusters includes a driving event record indicating a correlation between an acceleration event and a phone usage.
19. The non-transitory computer-readable storage medium of claim 16 , wherein the computer-executable instructions further cause the one or more processors to:
receive one or more feature inputs from a user computer device, wherein the one or more feature inputs indicate the one or more common features of the plurality of driving event records that should be analyzed in order to categorize and label the driving event records;
display information related to the at least two clusters to a user through the user computer device; and
receive one or more cluster labels from the user computer device, the one or more cluster labels indicating whether the driving event records in each cluster represent actual distracted driving events or passenger events.
20. The non-transitory computer-readable storage medium of claim 16 , wherein the computer-executable instructions further cause the at least one processor to:
assign a category to the new driving event as an actual distracted driving event or a passenger event; and
determine a confidence level to the category assigned to the new driving event.