Methods and systems for smart claim routing and smart claim assignment
AssigneeState Farm Mutual Automobile Insurance Company
InventorsJohn Westhues, Leann Dionesotes, David Ruby, John Dillard
Life of this patent
Estimating the term…
Abstract
A method of assigning and/or routing an auto claim to an appropriate claim handling tier to mitigate delay may include training a machine learning model using historical claim data to determine a severity corresponding to an injury claim, receiving a loss report corresponding to an auto accident, analyzing the loss report using the trained machine learning model to determine the severity of at least one injury corresponding to the loss report, determining an injury segment, and storing the indication of the injury segment in association with the loss report.
Claims20
A computer-implemented method of determining an injury segment based on the severity of the injury, comprising:
- training, via a processor, a machine learning model using historical claim data to determine a severity corresponding to an injury claim,
- receiving, via a processor, a loss report corresponding to an auto accident,
- analyzing the loss report corresponding to the auto accident using the trained machine learning model to determine the severity of at least one injury corresponding to the loss report,
- determining, based on the severity of the at least one injury claim corresponding to the loss report, an injury segment, and
- storing, via a processor, an indication of the injury segment in association with the loss report.
A computer system configured to determine an injury segment based on the severity of the injury, the system comprising one or more processors configured to:
- train, via the one or more processors, a machine learning model using historical claim data to determine a severity corresponding to an injury claim,
- receive, via the one or more processors, a loss report corresponding to an auto accident,
- analyze the loss report corresponding to the auto accident using the trained machine learning model to determine the severity of at least one injury corresponding to the loss report,
- determine, based on the severity of the at least one injury claim corresponding to the loss report, an injury segment, and
- store, via the one or more processors, an indication of the injury segment in association with the loss report.
A non-transitory computer readable medium containing program instructions that when executed, cause a computer to:
- train, via the one or more processors, a machine learning model using historical claim data to determine a severity corresponding to an injury claim,
- receive, via the one or more processors, a loss report corresponding to an auto accident,
- analyze the loss report corresponding to the auto accident using the trained machine learning model to determine the severity of at least one injury corresponding to the loss report,
- determine, based on the severity of the at least one injury claim corresponding to the loss report, an injury segment, and
- store, via the one or more processors, an indication of the injury segment in association with the loss report.
Dependencies are inferred from the claim text.