COMPUTER SYSTEM FOR APPLYING PREDICTIVE MODEL TO DETERMINATE AND INDETERMINATE DATA

• US 20090254379A1
• Filed: 04/08/2008
• Published: 10/08/2009
• Est. Priority Date: 04/08/2008
• Status: Active Grant

• Current Assignee: Hartford Fire Insurance Company (The Hartford Financial Services Group, Inc.)
• Original Assignee: Hartford Fire Insurance Company (The Hartford Financial Services Group, Inc.)
• Inventors: Ruotolo, James Dominic, McGoldrick, John Albert, Adams, Jonathan Kaleb
• Granted Patent: US 9,378,527 B2
• Time in Patent Office: Days
• US Class Current: 705/4
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 99/00 Subject matter not provided for in other groups of this subclass
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 20/4016 involving fraud or risk level assessment in transaction processing
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

A computer system includes a data storage module. The computer system also includes an indeterminate data capture module. The data storage module receives, stores, and provides access to both determinate data and indeterminate data that was captured by the indeterminate data capture module. The computer system also includes a computer processor and a program memory. The computer processor executes programmed instructions and stores and retrieves the data stored in the data storage module. The data stored in the data storage module is related to historical claim transactions and current claim transactions. A predictive model component is coupled to the data storage module, and determines whether to refer a current claim transaction to an investigation unit. A model training component is coupled to the computer processor and functions to train the predictive model.

Claims

1. A computer system comprising:

an indeterminate data capture module for capturing indeterminate data;

a data storage module in communication with the indeterminate data capture module, said data storage module for receiving, storing, and providing access to indeterminate data captured by the indeterminate data capture module, said data storage module also storing and providing access to determinate data, said indeterminate and determinate data stored by said data storage module related to historical claim transactions and to current claim transactions;

a predictive model component, coupled to the data storage module, for determining whether to identify a one of said current claim transactions for referral to an investigation unit;

a computer processor for executing programmed instructions and for storing and retrieving said data related to current claim transactions;

program memory, coupled to the computer processor, for storing program instruction steps for execution by the computer processor;

a model training component, coupled to the computer processor, for training the predictive model component based on the data related to the historical claim transactions in accordance with program instructions stored in the program memory and executed by the computer processor, thereby providing a trained predictive model component;

an output device, coupled to the computer processor, for outputting an output indicative of whether said one of said current claim transactions should be referred to the investigation unit, wherein the computer processor generates the output in accordance with program instructions in the program memory and executed by the computer processor, said output generated in response to application of data for said one of said current claim transactions to the trained predictive model component; and

a routing module for directing workflow based on the output from the output device.

2. The computer system of claim 1, wherein the indeterminate data capture module includes an optical character reader.

3. The computer system of claim 1, wherein the indeterminate data capture module includes a natural language processing module.

4. The computer system of claim 3, wherein the indeterminate data includes claim handlers'"'"' narrative text notes.

5. The computer system of claim 4, wherein the natural language processing module extracts claim handlers'"'"' opinions from the claim handlers'"'"' narrative text notes.

6. The computer system of claim 1, wherein the indeterminate data capture module includes a speech recognition module.

7. The computer system of claim 1, wherein:

the data for said one of said current claim transactions specifies a claimant; and

the indeterminate data includes a recording of the claimant'"'"'s voice.

8. The computer system of claim 7, wherein the indeterminate data capture module includes a component for analyzing the claimant'"'"'s voice.

9. The computer system of claim 1, wherein the indeterminate data includes at least one of:

(a) text captured by optical character reading;

(b) information extracted from text; and

(c) text converted from a voice signal.

10. The computer system of claim 1, wherein the routing module routes said one of the current claim transactions to the investigation unit based on the output from the output device.

11. The computer system of claim 10, wherein the routing module routes the current claim transaction to an investigative analyst in the investigation unit.

12. The computer system of claim 1, wherein the claim transactions are worker'"'"'s compensation claims.

13. The computer system of claim 1, wherein the claim transactions are bodily injury claims.

14. The computer system of claim 1, where the claim transactions are property damage claims.

15. A computer system comprising:

a data storage unit for receiving, storing and providing access to historical claim data and current claim data, the current claim data representing a plurality of current claim transactions;

a plurality of data input devices, in communication with the data storage unit, for supplying current claim data to the data storage unit, the plurality of data input devices including at least one data input device for capturing indeterminate data, the current claim data supplied to the data storage unit including the indeterminate data;

a computer processor in communication with the data storage unit; and

a program memory, coupled to the computer processor, for storing at least one application program, the at least one application program including program instruction steps for execution by the computer processor, the at least one application program including;

a predictive model that has been trained on and verified with the historical claim data and that controls the computer processor to analyze the current claim data in the data storage unit and to provide a respective output for each current claim transaction represented by the current claim data, the respective output indicating whether said each current claim transaction should be referred to an investigation unit; and

a routing component, responsive to the respective output for each of the current claim transactions, for selectively routing ones of the current claim transactions to the investigation unit.

16. The computer system of claim 15, wherein the computer processor, under control by the routing component, routes ones of the current claim transactions via electronic mail messages to the investigation unit.

17. The computer system of claim 16, wherein investigative analysts in the investigation unit are recipients of the electronic mail messages.

18. The computer system of claim 15, wherein the plurality of data input devices include an optical character reader for converting paper documents to text files.

19. The computer system of claim 18, wherein the at least one application program includes:

a data extraction component for controlling the computer processor to extract information from the text files.

20. The computer system of claim 15, wherein:

the indeterminate data includes claim handlers'"'"' narrative text notes; and

the at least one application program includes;

a data extraction component for controlling the computer processor to extract information from the claim handlers'"'"' narrative text notes.

21. The computer system of claim 20, wherein the extracted information includes information indicative of the claim handlers'"'"' opinions

22. The computer system of claim 15, wherein:

the indeterminate data includes audio information files, the audio information files including recordings of claimants'"'"' voices; and

the at least one application program includes;

a component for controlling the computer processor to analyze the claimants'"'"' voices.

23. A method of operating a computer system, the method comprising:

using a plurality of input devices to provide determinate data and indeterminate data with respect to a first group of claim transactions;

processing the indeterminate data to extract information from the indeterminate data;

storing, in a computer storage unit, the determinate data and the information extracted from the indeterminate data as historical claim data;

using the historical claim data to train and verify a predictive model, the predictive model for evaluating claim transactions to determine whether to refer the claim transactions to an investigation unit;

using the plurality of input devices to provide determinate data and indeterminate data for current claim transactions;

processing the indeterminate data for the current claim transactions to extract information from the indeterminate data for the current claim transactions;

storing, in the computer storage unit, the determinate data for the current claim transactions and the information extracted from the indeterminate data for the current claim transactions;

applying the trained and verified predictive model to the determinate data for the current claim transactions and to the information extracted from the indeterminate data for the current claim transactions, to generate a respective output for each of the current claim transactions; and

selectively routing ones of the current claim transactions to an investigative unit based on the outputs generated by the predictive model.

24. The method of claim 23, wherein the processing the indeterminate data includes applying optical character recognition.

25. The method of claim 23, wherein the processing the indeterminate data includes parsing text files.

26. The method of claim 23, wherein the processing the indeterminate data includes applying natural language processing to text files.

27. The method of claim 26, wherein the extracted information includes claim handlers'"'"' opinions.

28. The method of claim 23, wherein the processing the indeterminate data includes analyzing recordings of claimants'"'"' voices.