Methods and systems for injury segment determination

1. A computer-implemented method of determining an injury segment, comprising:

receiving, via one or more processors, an auto accident loss report;

analyzing the loss report using a machine learning model to determine a severity of an injury relating to the loss report,

wherein analyzing the loss report includes:

extracting fields of the loss report, the fields include a photograph of an auto accident, a description of the auto accident, a vehicle type involved in the auto accident, or a weather report of a time of the auto accident;

encoding the extracted fields into a tensor, array, or a matrix; and

inputting the tensor, array, or a matrix into the machine learning model to obtain an output indicating the severity of the injury; and

wherein the machine learning model includes a plurality of parameters and is trained by:

initializing the plurality of parameters to random values;

inputting a plurality of tensors, arrays, or matrices to the machine learning model to obtain output values, wherein the plurality of tensors, arrays, or matrices (i) are labelled with expected output values, respectively, and (ii) includes claim records, in disparate formats from different time periods, including one or more of policy information, loss information, and injury information, and links to additional data including one or more of loss reports, photographs, investigator's reports, diagrams, legal pleadings, and electronic medical records; and

iteratively updating the plurality of parameters based on differences between the output values and respective expected output values until the output values converge to the respective expected output values;

determining, based on the severity of the injury, an injury segment; and

storing, via the one or more processors, an indication of the injury segment.

2. The computer-implemented method of claim 1 , wherein determining, based on the severity of the injury, the injury segment includes assigning the loss report to one or more tiers.

3. The computer-implemented method of claim 2 , wherein the one or more tiers are hierarchically related.

4. The computer-implemented method of claim 1 , wherein determining, based on the severity of the injury, the injury segment includes assigning the loss report to one or more ordered tiers, to create a routing.

5. The computer-implemented method of claim 4 , wherein the one or more ordered tiers are hierarchically related.

6. The computer-implemented method of claim 1 , wherein the severity is expressed by a numeric severity level.

7. The computer-implemented method of claim 1 , wherein the machine learning model is an artificial neural network.

8. The computer-implemented method of claim 1 , wherein the loss report includes one or both of (i) a photograph corresponding to an accident, and (ii) a textual description corresponding to the accident.

9. The computer-implemented method of claim 1 , wherein analyzing the loss report using the machine learning model to determine the severity of the injury includes analyzing electronic claim records corresponding to an accident.

10. The computer-implemented method of claim 9 , further comprising:

analyzing vehicle telematics information.

11. A computer system configured to determine an injury segment, the system comprising one or more processors configured to:

receive, via the one or more processors, an auto accident loss report;

analyze the loss report using a machine learning model to determine a severity of an injury relating to the loss report,

wherein analyzing the loss report includes:

extracting fields of the loss report, the fields include a photograph of an auto accident, a description of the auto accident, a vehicle type involved in the auto accident, or a weather report of a time of the auto accident;

encoding the extracted fields into a tensor, array, or a matrix; and

inputting the tensor, array, or a matrix into the machine learning model to obtain an output indicating the severity of the injury; and

wherein the machine learning model includes a plurality of parameters and is trained by:

initializing the plurality of parameters to random values;

inputting a plurality of tensors, arrays, or matrices to the machine learning model to obtain output values, wherein the plurality of tensors, arrays, or matrices (i) are labelled with expected output values, respectively, and (ii) includes claim records, in disparate formats from different time periods, including one or more of policy information, loss information, and injury information, and links to additional data including one or more of loss reports, photographs, investigator's reports, diagrams, legal pleadings, and electronic medical records; and

iteratively updating the plurality of parameters based on differences between the output values and respective expected output values until the output values converge to the respective expected output values;

determine, based on the severity of the injury, an injury segment; and

store, via the one or more processors, an indication of the injury segment.

12. The computer system of claim 11 , further configured to:

determine a routing and route the injury claim via the routing.

13. The computer system of claim 11 , wherein the machine learning model is an artificial neural network.

14. The computer system of claim 11 , further configured to:

analyze vehicle telematics information.

15. A non-transitory computer readable medium containing program instructions that when executed, cause a computer to:

receive an auto accident loss report;

analyze the loss report using a machine learning model to determine a severity of an injury relating to the loss report,

wherein analyzing the loss report includes:

extracting fields of the loss report, the fields include a photograph of an auto accident, a description of the auto accident, a vehicle type involved in the auto accident, or a weather report of a time of the auto accident;

encoding the extracted fields into a tensor, array, or a matrix; and

inputting the tensor, array, or a matrix into the machine learning model to obtain an output indicating the severity of the injury; and

wherein the machine learning model includes a plurality of parameters and is trained by:

initializing the plurality of parameters to random values;

inputting a plurality of tensors, arrays, or matrices to the machine learning model to obtain output values, wherein the plurality of tensors, arrays, or matrices (i) are labelled with expected output values, respectively, and (ii) includes claim records, in disparate formats from different time periods, including one or more of policy information, loss information, and injury information, and links to additional data including one or more of loss reports, photographs, investigator's reports, diagrams, legal pleadings, and electronic medical records; and

iteratively updating the plurality of parameters based on differences between the output values and respective expected output values until the output values converge to the respective expected output values;

determine, based on the severity of the injury, an injury segment; and

store an indication of the injury segment.

16. The non-transitory computer readable medium of claim 15 , containing further program instructions that when executed, cause a computer to:

determine a routing and route the injury claim via the routing.

17. The non-transitory computer readable medium of claim 15 , containing further program instructions that when executed, cause a computer to:

analyze vehicle telematics information.

18. The non-transitory computer readable medium of claim 15 , wherein the machine learning model is an artificial neural network.

19. The computer-implemented method of claim 1 , wherein the auto accident loss report is received from a user device, the method further comprising:

receiving location data from the user device; and

selecting the machine learning model based on the location data from a plurality of machine learning models.

20. The computer system of claim 11 , wherein the auto accident loss report is received from a user device, the one or more processors further configured to:

receive location data from the user device; and

select the machine learning model based on the location data from a plurality of machine learning models.

21. The computer system of claim 11 , further configured to:

assign the loss report to one or more tiers.

22. The non-transitory computer readable medium of claim 15 , containing further program instructions that when executed, cause a computer to:

assign the loss report to one or more tiers.

23. The non-transitory computer readable medium of claim 15 , wherein the auto accident loss report is received from a user device, the non-transitory computer readable medium containing further program instructions that when executed, cause a computer to:

receive location data from the user device; and

select the machine learning model based on the location data from a plurality of machine learning models.