Granted Patent B2

US 12,579,582 · App. 18/505,704 · Granted Mar 17, 2026

Inventors: Loren Naim Falandino (Superior Township, MI); Thomas Allen Seward (Ann Arbor, MI); Bradley Keith Goodyear (Superior Township, MI)

Assignee: Insurance Quantified, LLC

G06Q40/08G06Q10/06311

Abstract

Claims (30)

1 . A system comprising:

at least one computer hardware processor; and

at least one non-transitory computer readable storage medium, storing processor-executable instructions, that, when executed by the at least computer hardware processor causes the at least one computer hardware processor to perform a method comprising:

obtaining a plurality of input digital document entities including insurance claims data related to a subject insurance claim;

analyzing the plurality of input digital document entities to determine one or more workflows for processing at least one of the plurality of document entities;

processing the at least one of the plurality of document entities according to the one or more workflows, the processing comprising:

analyzing the at least one of the plurality of digital document entities to determine whether one or more human-in-the-loop tasks are to be performed on at least a portion of the at least one of the plurality of document entities; and

when it is determined that one or more human-in-the-loop tasks are to be performed:

generating an interactive graphical user interface (GUI) including the one or more human-in-the-loop tasks to be performed for processing the portion of the at least one of the plurality of document entities;

displaying the interactive GUI;

obtaining, via the interactive GUI, digital document data corresponding to the portion of at least one of the plurality of document entities processed according to the one or more human-in-the-loop tasks; and

updating the digital document entities based on the digital document data corresponding to the portion of the at least one of the plurality of document entities;

extracting a plurality of insurance claims features from the updated digital document entities;

analyzing the insurance claims data and insurance claims features using at least one machine learning model trained on a plurality of insurance loss claim records to predict a loss for the subject insurance claim;

generating a deliverable data product using the predicted loss, insurance claims data, and/or extracted insurance claims features; and

providing the deliverable data product to one or more external systems.

2 . The system according to claim 1 , wherein at least one of the one or more human-in-the-loop tasks includes a quality assurance annotation performed by at least one user.

3 . The system according to claim 1 , wherein the at least one non-transitory computer readable storage medium stores further instructions that cause the processer to perform, before the analyzing, routing input documents or portions of input documents to one or more workflows.

4 . The system according to claim 3 , wherein the routing is performed based on a classification of the input documents or portions of input documents.

5 . The system according to claim 3 , the routing comprises routing the input documents or portions of input documents to a specific user to perform a reviewing action.

6 . The system according to claim 3 , wherein the routing comprises generating one or more tasks for processing the digital input document entities or portions of input document entities.

7 . The system according to claim 6 , wherein the one or more tasks comprise a plurality of parallel tasks to support processing of a single document entity.

8 . The system according to claim 6 , wherein generating the tasks is performed based on at least one of: quality metrics, random sampling, logical data check, and other properties of a subject input document or portion of the subject input document.

9 . The system according to claim 1 , the one or more human-in-the-loop tasks comprise annotating data elements of the at least one of the plurality of document entities.

10 . The system according to claim 1 , wherein the deliverable data product further comprises one or more of:

a risk measure in relation to a claim; and

a scoring parameter in relation to the claim.

11 . The system according to claim 1 , wherein the at least one machine learning model is configured to predict loss in relation to the subject insurance claim based on closed claims data.

12 . The system according to claim 1 , wherein the at least one non-transitory computer readable storage medium stores further instructions that cause the processer to perform: analyzing the insurance claims data and insurance claims features using at least one machine learning model configured to predict loss in relation to the subject insurance claim based on open claims data.

13 . The system according to claim 1 , wherein the at least one machine learning model configured to predict loss in relation to a subject insurance claim is configured to train on a training data set defined across insurance carriers in a commercial insurance industry.

Assignments (4)

Continuity (2)

References Cited (30)