Patent Issued for Implementing machine learning for life and health insurance claims handling (USPTO 11783422): State Farm Mutual Automobile Insurance Company

2023 OCT 30 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- According to news reporting originating from Alexandria, Virginia, by NewsRx journalists, a patent by the inventors Christopulos, Nicholas U. (Bloomington, IL, US), Donahue, Erik (Normal, IL, US), Goldfarb, Meghan Sims (Bloomington, IL, US), Hayward, Gregory L (Bloomington, IL, US), filed on September 20, 2018, was published online on October 10, 2023.

The assignee for this patent, patent number 11783422, is State Farm Mutual Automobile Insurance Company (Bloomington, Illinois, United States).

Reporters obtained the following quote from the background information supplied by the inventors: “Historically, a claim relating to a life, worker’s compensation, disability, and/or health insurance policy may be reported to an issuer of the insurance policy (e.g., an insurance company) upon the occurrence of an event covered under the policy. The claim may be allocated to a claims examiner who may manage the claim. For example, the claims examiner may manually update paper and/or electronic files related to the reported, or filed, claim as claim information is provided by the claimant, and/or collected by the insurer. The claims examiner may conduct an investigation and may contact the policy holder/claimant and/or others (e.g., beneficiaries, witnesses, government employees, third parties, etc.).

“In many instances, the claim handling process may include time-consuming and fact-intensive processes and procedures. However, insurers are motivated to timely investigate and pay claims promptly. At the same time, insurers are also motivated to identify fraudulent claims or buildup, so as to not penalize all customers with higher rates.”

In addition to obtaining background information on this patent, NewsRx editors also obtained the inventors’ summary information for this patent: “The present disclosure generally relates to methods and systems for implementing machine learning to improve upon aspects of life, worker’s compensation, disability, and/or health insurance claim processing and handling throughout the claims lifecycle. In some embodiments, neural networks may be used. Other machine learning techniques, including those discussed elsewhere herein may also be employed. Embodiments of exemplary systems and computer-implemented methods are described below.

“In one aspect, a computer-implemented method of automated claims handling may include (1) receiving a set of labeled historical claims (including life, worker’s compensation, disability, and/or health claims), each one corresponding to a respective adjusted settlement amount. The method may include (2) training an artificial neural network using a subset of the labeled historical claims and/or each respective adjusted settlement amount. The method may then include (3) receiving a life, worker’s compensation, disability, and/or health claim from a user, such as from their mobile device; (4) analyzing the life, worker’s compensation, disability, and/or health claim using the trained artificial neural network to determine a claim settlement prediction; and (5) generating, based upon the settlement prediction, a settlement offer. The method may also include (6) transmitting the settlement offer to an application in a user mobile or other device, such as via wireless communication or data transmission. The method may include additional, less, or alternate actions.

“In another aspect, a claim handling system may include one or more processors and one or more memories storing instructions. When the instructions are executed by the one or more processors, they may cause the claim handling system to (1) receive a set of life or health claim information from the user; (2) predict a claim settlement amount by analyzing the set of life or health claim information using a trained artificial network; (3) generate a settlement offer based upon the claim settlement amount; (4) display the settlement offer in the user device; and/or (5) receive a manifestation of acceptance from the user device. The system may include additional, less, or alternate functionality, including that discussed elsewhere herein.

“Advantages will become more apparent to those skilled in the art from the following description of the preferred embodiments which have been shown and described by way of illustration. As will be realized, the present embodiments may be capable of other and different embodiments, and their details are capable of modification in various respects. Accordingly, the drawings and description are to be regarded as illustrative in nature and not as restrictive.

“The figures depict preferred embodiments for purposes of illustration only. One skilled in the art will readily recognize from the following discussion that alternative embodiments of the systems and methods illustrated herein may be employed without departing from the principles of the invention described herein.”

The claims supplied by the inventors are:

“1. A computer-implemented method of claims handling, comprising: receiving a set of labeled historical claims, each labeled historical claim of the set of labeled historical claims corresponding to a respective adjusted settlement amount and a label, the label being one of a plurality of predetermined labels; training a plurality of first artificial neural networks using a first subset of the set of labeled historical claims; training a second artificial neural network using a second subset of the set of labeled historical claims and the respective adjusted settlement amount for each labeled historical claim of the second subset of the labeled historical claims, the first subset of the set of labeled historical claims being different from the second subset of the set of labeled historical claims; receiving, from a user, a life claim, the life claim comprising at least one selected from a group consisting of image data and audio data; and analyzing the life claim using the plurality of trained first artificial neural networks and the trained second artificial neural network to determine a claim settlement prediction by at least: extracting text-based content from the at least one selected from a group consisting of image data and audio data in the life claim using at least a natural language processing model; selecting a trained first artificial neural network from the plurality of trained first artificial neural networks based on the extracted text-based content; inputting the extracted text-based content to the selected trained first artificial neural network; determining a claim label representing a category of the life claim using the selected trained first artificial neural network based at least in part on the extracted text-based content, the claim label being one of the plurality of predetermined labels; inputting the extracted text-based content and the determined claim label to the trained second artificial neural network; and determining the claim settlement prediction using the trained second artificial neural network based at least in part on the extracted text-based content and the determined claim label.

“2. The computer-implemented method of claim 1, wherein the adjusted settlement amount is an inflation-adjusted amount.

“3. The computer-implemented method of claim 1, wherein the life claim corresponds to a life insurance policy.

“4. The computer-implemented method of claim 3, wherein the life claim includes a photograph of a death certificate of a deceased person under an insurance policy related to the life claim.

“5. The computer-implemented method of claim 1, wherein the life claim corresponds to one or both of (i) a worker’s compensation insurance policy, and (ii) a disability insurance policy.

“6. The computer-implemented method of claim 5, wherein the life claim includes a medical bill under a health insurance policy related to the life claim.

“7. The computer-implemented method of claim 1, further comprising: generating, based upon the claim settlement prediction, a settlement offer; wherein the settlement offer includes one of (i) a lump sum payment, or (ii) a series of installment payments.

“8. The computer-implemented method of claim 7, further comprising: transmitting the settlement offer to an application in a user device; and displaying, in the user device, the settlement offer.

“9. The computer-implemented method of claim 8, further comprising: receiving, from the user device, a manifestation of acceptance of the settlement offer.

“10. The computer-implemented method of claim 8, wherein displaying, in the user device, the settlement offer comprises displaying a binary choice between (i) a lump sum payment, and (ii) a series of installment payments.

“11. The computer-implemented method of claim 8, further comprising: generating, in association with an account of a beneficiary under an insurance policy associated with the life claim, an automatic payment of money corresponding to the claim settlement prediction.

“12. A claims handling user device, comprising: one or more processors; one or more memories comprising a claim handling application that, when executed by the one or more processors, causes the one or more processors to: receive a set of labeled historical claims, each labeled historical claim of the set of labeled historical claims corresponding to a respective adjusted settlement amount and a label, the label being one of a plurality of predetermined labels, train a plurality of first artificial neural networks using a first subset of the set of labeled historical claims, train a second artificial neural network using a second subset of the set of labeled historical claims and the respective adjusted settlement amount for each labeled historical claim of the second subset of the labeled historical claims, the first subset of the set of labeled historical claims being different from the second subset of the set of labeled historical claims, receive a set of life claim information from a user, the set of life claim information comprising at least one selected from a group consisting of image data and audio data, predict a claim settlement amount by analyzing the set of life claim information using the plurality of trained first artificial neural networks and the trained second artificial network by at least: extracting text-based content from the at least one selected from a group consisting of image data and audio data in the set of life claim information using at least a natural language processing model, selecting a trained first artificial neural network from the plurality of trained first artificial neural networks based on the extracted text-based content, inputting the extracted text-based content to the selected trained first artificial neural network, determining a claim label representing a category of the set of life claim information using the selected trained first artificial neural network based at least in part on the extracted text-based content, the claim label being one of the plurality of predetermined labels, inputting the extracted text-based content and the determined claim label to the trained second artificial neural network, and predicting the claim settlement amount using the trained second artificial neural network based at least in part on the extracted text-based content and the determined claim label, generate, based upon the claim settlement amount, a settlement offer, display, in a user device, the settlement offer; and receive, from the user device, a manifestation of acceptance.

“13. The claims handling user device of claim 12, wherein the application further causes the one or more processors to: transmit the set of life claim information to a remote server, and receive, from the remote server, the claim settlement amount.

“14. The claims handling user device of claim 12, wherein the application further causes the one or more processors to: generate a payment to an account of a beneficiary associated with an insurance policy associated with the life claim.

“15. The claims handling user device of claim 12, wherein the set of life claim information is a first set of life claim information, and the application further causes the one or more processors to: receive a second set of life claim information, pre-fill a user interface in the user device using the second set of life information, and transmit the first set of life claim information and the second set of life claim information to a remote server.

“16. A non-transitory computer readable medium containing computer instructions that, when executed, cause a computer to: receive a set of labeled historical claims, each labeled historical claim of the set of labeled historical claims corresponding to a respective adjusted settlement amount and a label, the label being one of a plurality of predetermined labels, train a plurality of first artificial neural networks using a first subset of the set of labeled historical claims, train a second artificial neural network using a second subset of the set of labeled historical claims and the respective adjusted settlement amount for each labeled historical claim of the second subset of the labeled historical claims, the first subset of the set of labeled historical claims being different from the second subset of the set of labeled historical claims, receive a set of life claim information from a device of a user, the set of life claim information comprising at least one selected from a group consisting of image data and audio data, predict a claim settlement amount by analyzing the set of life claim information using the plurality of trained first artificial neural networks and the trained second artificial network by at least: extracting text-based content from the at least one selected from a group consisting of image data and audio data in the set of life claim information using at least a natural language processing model, selecting a trained first artificial neural network from the plurality of trained first artificial neural networks based on the extracted text-based content, inputting the extracted text-based content to the selected trained first artificial neural network, determining a claim label representing a category of the set of life claim information using the selected trained first artificial neural network based at least in part on the extracted text-based content, inputting the extracted text-based content and the determined claim label to the trained second artificial neural network, and predicting the claim settlement amount using the trained second artificial neural network based at least in part on the extracted text-based content and the determined claim label, generate, based upon the claim settlement amount, a settlement offer, transmit, to the device of the user, the settlement offer, and receive, from the device of the user, a manifestation of acceptance.”

There are additional claims. Please visit full patent to read further.

For more information, see this patent: Christopulos, Nicholas U. Implementing machine learning for life and health insurance claims handling. U.S. Patent Number 11783422, filed September 20, 2018, and published online on October 10, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11783422)&db=USPAT&type=ids

(Our reports deliver fact-based news of research and discoveries from around the world.)