Patent Issued for Dialogue advisor for claim loss reporting tool (USPTO 11915319): State Farm Mutual Automobile Insurance Company

2024 MAR 14 (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 Devore, Justin (Atlanta, IL, US), King, Garren (Eureka, IL, US), Mathes, Andrew (Eureka, IL, US), filed on April 27, 2021, was published online on February 27, 2024.

The assignee for this patent, patent number 11915319, is State Farm Mutual Automobile Insurance Company (Bloomington, Illinois, United States).

Reporters obtained the following quote from the background information supplied by the inventors: “When a loss occurs, for example via an automobile accident or other type of incident, an individual can contact a representative of an insurance company to report the loss and/or file an insurance claim. For example, a caller, such as a customer of the insurance company, a third-party claimant, or another party, can call a claim handler or other representative of the insurance company. The representative may ask the caller questions about the loss to obtain information about the loss. For example, the representative may ask the caller when an accident occurred, where the accident occurred, which parties were involved in the accident, and/or other questions. The representative can enter information received from the caller into a loss report, such as a “first notice of loss” (FNOL) or other type of report associated with an insurance claim.

“In some situations, representatives may use claim loss reporting tools when initially speaking to callers about reported losses. For example, a representative can use a software-based claim loss reporting tool via user interface (UI) on a computer or other device. During a call or other communication session with a caller, a representative can use the UI to enter information about the loss into the claim loss reporting tool. The claim loss reporting tool, or an associated component, can thus use the entered information to generate a loss report. The UI of a claim loss reporting tool may display questions that the representative should ask the caller, or otherwise identify missing information that the representative should ask about, during a communication session with the caller.

“In some existing systems, the claim loss reporting tool displays suggested questions based on a pre-written script and/or a preconfigured and static logic tree. For example, some existing claim loss reporting tools can have a static logic tree such that if a caller answers “yes” to a certain predefined question, the claim loss reporting tool may follow a corresponding branch of the static logic tree to suggest that the representative ask one or more predefined follow-up questions in that branch of the logic tree.

“After a loss report associated with an insurance claim has been taken, the insurance claim can be routed for further processing to a department or group in the insurance company, or a specific claim handler, for further processing. A decision about where to route a new insurance claim for further processing can be based, at least in part, on information about the claim that has been recorded by the representative in the loss report. For instance, if a loss report associated with a new insurance claim indicates that multiple parties were involved in an accident, a claim routing system may determine that a claim handler who specializes in subrogation and/or comparative negligence issues may be more suited to handle that new insurance claim than another claim handler who has less experience with those types of issues.

“However, if not enough questions, and/or insufficient questions, are asked when a representative takes a loss report, the loss report may not include sufficient information for a routing system to make an optimal claim routing decision. Accordingly, a claim may be routed to a destination that may process the claim more slowly, and/or with inferior results, than another destination could have processed the claim.

“For example, a situation associated with a loss may have involved multiple parties. If a representative did not ask questions that might reveal a potential that comparative negligence issues may be associated with the loss, the loss report may not include enough information for a claim routing system to determine that the claim may involve such comparative negligence issues. Accordingly, due to insufficient information in the loss report about the potential for comparative negligence, the claim routing system may not recognize the potential for comparative negligence in the claim. The claim routing system may in turn route the insurance claim to a first claim handler with a relatively low amount of experience handling comparative negligence issues, even though a second claim handler with more experience handling comparative negligence issues may have been able to process the insurance claim faster and/or with better results. In various examples, the first claim handler who is initially assigned the claim may take longer to process the claim than the second claim hander would have, or the first claim handler may choose to later reassign the claim to the second claim handler once the first claim handler determines that the second claim handler is better suited to handle the claim. This can lead to increased claim processing times overall, increased usage of computing resources by both the first claim handler and the second claim handler, and increased usage of network bandwidth to transmit claim data between computing devices associated with the first claim handler and the second claim handler.

“The example systems and methods described herein may be directed toward mitigating or overcoming one or more of the deficiencies described above.”

In addition to obtaining background information on this patent, NewsRx editors also obtained the inventors’ summary information for this patent: “The systems and methods described herein can be used to identify questions that can be asked, during an initial communication session between a representative and a caller associated with an insurance claim, that can lead to an increased confidence level in a claim destination prediction made by a claim router. The systems and methods described herein can also identify an action that can be taken by the representative, during the initial communication session, when a confidence level in a destination prediction is likely to be above a threshold, instead of waiting to perform that action during a second communication session after the claim has been routed to a destination. Overall, the systems and methods described herein can increase efficiency and reduce delays in claim intake systems and claims handling processes overall.

“According to a first aspect, a computer-implemented method can include generating, by one or more processors, a preliminary destination prediction of a destination, selected from a set of possible destinations, for claim data associated with an insurance claim. The preliminary destination prediction can be generated based on current information in a loss report associated with the insurance claim, and can be associated with a first confidence level. The method can also include identifying, by the one or more processors, an empty field in the loss report, and determining, by the one or more processors, a set of possible values for the empty field. The method can further include generating, by the one or more processors, one or more theoretical destination predictions, wherein the one or more theoretical destination predictions have second confidence levels and are based on the current information in the loss report and the set of possible values for the empty field. The method can also include determining, by the one or more processors, that the second confidence levels of the one or more theoretical destination predictions are greater than the first confidence level of the preliminary destination prediction. The method can also include causing, by the one or more processors, a claim loss reporting tool to display at least one user interface element that requests a value for the empty field, based on determining that the second confidence levels are greater than the first confidence level.

“According to a second aspect, a computer-implemented method can include generating, by one or more processors, a preliminary destination prediction of a likely destination, selected from a set of possible destinations, for claim data associated with an insurance claim. The preliminary destination prediction can be generated based on current information in a loss report associated with the insurance claim, and can be associated with a confidence level. The method can also include determining, by the one or more processors, that the confidence level is above a predefined threshold. The method can further include identifying, by the one or more processors, an action associated with the likely destination. The method can also include causing, by the one or more processors, a claim loss reporting tool to display a prompt requesting that a representative perform the action during a current communication session between the representative and a caller.

“According to a third aspect, one or more computing devices can comprise at least one processor and memory storing computer executable instructions that, when executed by the at least one processor, cause the at least one processor to perform operations. The operations can include accepting user input, via a claim loss reporting tool, from a representative during a communication session with a caller. The user input can be associated with a loss reported by the caller. The operations can also include generating a loss report associated with an insurance claim, based on the user input. The operations can further include generating simulated destination predictions of a destination, selected from a set of possible destinations, for claim data associated with the insurance claim, based on the loss report. The simulated destination predictions can correspond with destination predictions that a claim router would generate based on the loss report. The operations can also include displaying, via the claim loss reporting tool, one or more of a user interface element or a prompt. The user interface element can request additional user input, during the communication session, associated with a currently-empty field of the loss report. The prompt can request performance of an action, by the representative during the communication session, associated with the destination indicated in at least one of the simulated destination predictions.”

The claims supplied by the inventors are:

“1. A computer-implemented method, comprising: generating, by one or more processors, and based on input provided via a claim loss reporting tool during a communication session associated with an insurance claim, a loss report associated with the insurance claim; generating, by the one or more processors, and during the communication session, a preliminary destination prediction of a destination, selected from a set of possible destinations, for claim data associated with the insurance claim, wherein: the preliminary destination prediction is generated, by a dialogue advisor machine learning model associated with the claim loss reporting tool, based on current information in the loss report, the dialogue advisor machine learning model is an instance of a machine learning model that a claim router, different from the claim loss reporting tool, is configured to use following completion of the communication session to generate a final destination prediction indicating the destination for the claim data, and the preliminary destination prediction, generated based on the current information, is associated with a first confidence level; identifying, by the one or more processors, and during the communication session, an empty field in the loss report based on the current information; determining, by the one or more processors, and during the communication session, a set of possible values for the empty field; generating, by the one or more processors, during the communication session, and using the dialogue advisor machine learning model, one or more theoretical destination predictions that: have second confidence levels, and are based on the current information in the loss report in combination with individual values, of the set of possible values, for the empty field; determining, by the one or more processors, and during the communication session, that the second confidence levels of the one or more theoretical destination predictions are greater than the first confidence level of the preliminary destination prediction; determining, by the one or more processors, during the communication session, and based on determining that the second confidence levels are greater than the first confidence level, that filling the empty field with a value would increase a confidence level of the final destination prediction generated by the claim router following the completion of the communication session; and causing, by the one or more processors, and based on determining that filling the empty field would increase the confidence level of the final destination prediction, a user interface of the claim loss reporting tool to display, during the communication session, at least one user interface element that requests that the empty field be filled, wherein the machine learning model is trained, based on a training data set associated with assignments of previous insurance claims to destinations based on corresponding loss reports, to identify features that are predictive of the destinations that processed the previous insurance claims.

“2. The computer-implemented method of claim 1, wherein the at least one user interface element comprises suggested text of a question associated with the empty field.

“3. The computer-implemented method of claim 1, further comprising: receiving, by the one or more processors, and based on second input provided via the claim loss reporting tool, the value for the empty field; adjusting, by the one or more processors, the loss report based on the value; generating, by the one or more processors, and via the claim router using the machine learning model based on the loss report, the final destination prediction indicating the destination for the claim data; selecting, by the one or more processors, the destination for the claim data based on the final destination prediction; and routing, by the one or more processors, the claim data to the destination.

“4. The computer-implemented method of claim 1, wherein the set of possible destinations includes a plurality of groups of one or more workers available to process the claim data within an insurance company.

“5. The computer-implemented method of claim 1, wherein the at least one user interface element comprises a notification associated with the empty field.

“6. The computer-implemented method of claim 1, further comprising: receiving, by the one or more processors, additional data indicating downstream impacts of displaying, via the user interface of the claim loss reporting tool, particular user interface elements that request that corresponding empty fields of the loss report be filled, during previous communication sessions; and re-training, by the one or more processors, the machine learning model based on the additional data.

“7. The computer-implemented method of claim 1, further comprising: determining, by the one or more processors, and during the communication session, that the first confidence level of the preliminary destination prediction is above a threshold; identifying, by the one or more processors, during the communication session, and based on determining that the first confidence level is above the threshold, an action associated with the destination indicated by the preliminary destination prediction; and causing, by the one or more processors, the user interface of the claim loss reporting tool to display at least one second user interface element instructing a user of the claim loss reporting tool to perform the action during the communication session.

“8. One or more computing devices, comprising: at least one processor; and memory storing computer-executable instructions associated with a claim loss reporting tool that, when executed by the at least one processor, cause the at least one processor to perform operations comprising: generating, based on input provided via the claim loss reporting tool during a communication session associated with an insurance claim, a loss report associated with the insurance claim; generating, during the communication session, a preliminary destination prediction of a destination, selected from a set of possible destinations, for claim data associated with the insurance claim, wherein: the preliminary destination prediction is generated, by a dialogue advisor machine learning model associated with the claim loss reporting tool, based on current information in the loss report, the dialogue advisor machine learning model is an instance of a machine learning model that a claim router, different from the claim loss reporting tool, is configured to use following completion of the communication session to generate a final destination prediction indicating the destination for the claim data, and the preliminary destination prediction, generated based on the current information, is associated with a first confidence level; identifying, during the communication session, an empty field in the loss report based on the current information; determining, during the communication session, a set of possible values for the empty field; generating, during the communication session, and using the dialogue advisor machine learning model, one or more theoretical destination predictions that: have second confidence levels, and are based on the current information in the loss report in combination individual values, of the set of possible values for the empty field; determining, during the communication session, that the second confidence levels of the one or more theoretical destination predictions are greater than the first confidence level of the preliminary destination prediction; determining, during the communication session, and based on determining that the second confidence levels are greater than the first confidence level, that filling the empty field with a value would increase a confidence level of the final destination prediction generated by the claim router following the completion of the communication session; and causing, based on determining that filling the empty field would increase the confidence level of the final destination prediction, a user interface of the claim loss reporting tool to display, during the communication session, a prompt requesting that the empty field be filled, wherein the machine learning model is trained, based on a training data set associated with assignments of previous insurance claims to destinations based on corresponding loss reports, to identify features that are predictive of the destinations that processed the previous insurance claims.

“9. The one or more computing devices of claim 8, wherein the prompt comprises suggested text of a question associated with the empty field.

“10. The one or more computing devices of claim 8, wherein the prompt comprises a notification associated with the empty field.

“11. The one or more computing devices of claim 8, wherein the operations further comprise: receiving, based on second input provided via the claim loss reporting tool the value for the empty field; adjusting the loss report based on the value; and providing the loss report to the claim router, to cause the claim router to: generate, using the machine learning model based on the loss report, the final destination prediction indicating the destination for the claim data; select the destination for the claim data based on the final destination prediction; and route the claim data to the destination.

“12. The one or more computing devices of claim 8, wherein the set of possible destinations includes a plurality of groups of one or more workers available to process the claim data within an insurance company.”

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

For more information, see this patent: Devore, Justin. Dialogue advisor for claim loss reporting tool. U.S. Patent Number 11915319, filed April 27, 2021, and published online on February 27, 2024. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11915319)&db=USPAT&type=ids

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