US-20260127677-A1 - DYNAMIC ADAPTATION OF MITIGATIVE CONTENT DATA BASED ON MACHINE LEARNING ENGAGEMENT MONITORING

Abstract

A computing system can facilitate a set of interactive sessions in which respective users engage with interactive mitigation content prior to a catastrophic event. The system initiates a live engagement monitor implementing machine learning during each session to receive engagement data from the computing devices of each of the users, and dynamically adapts the interactive mitigation content to induce or increase user engagement by the users with the interactive mitigation content and encourage each of the users perform a customized set of tasks prior to the catastrophic event. Based in part on feedback data corresponding to these customized tasks, the system generates an exposure risk set for a common policy provider of the set of users.

Inventors

• Justin Lewis-Weber
• Theo Patt

Assignees

• Assured Insurance Technologies, Inc.

Dates

Publication Date

20260507

Application Date

20251113

Claims (1)

1. 1 . A computing system comprising: a network communication interface; one or more processors; and a memory storing instructions that, when executed by the one or more processors, cause the computing system to: determine a set of users that utilize a common policy provider and are predicted to be affected by a catastrophic event; for each respective user of the set of users, determine a set of unique property characteristics of the respective user; based on the unique property characteristics of the respective user, transmit, over one or more networks, interactive content data to a computing device of the respective user, the interactive content data causing the computing device of the respective user to present interactive mitigation content comprising a customized set of tasks to perform, based on the unique property characteristics of the respective user, to mitigate and/or prevent loss resulting from the catastrophic event; during each of one or more interactive sessions in which the respective user engages with the interactive mitigation content, initiate a live engagement monitor implementing machine learning to (i) receive, over the one or more networks, engagement data from the computing device of the respective user, the engagement data indicating interactions by the respective user with the interactive mitigation content presented on the computing device of the respective user, and (ii) based on the engagement data from the computing device of the respective user, dynamically adapt the interactive mitigation content to induce or increase user engagement by the respective user with the interactive mitigation content and encourage performance of the customized set of tasks; receive, over the one or more networks, feedback data from the computing device of the respective user, the feedback data indicating whether the respective user has performed one or more of the customized set of tasks prior to the catastrophic event; based at least in part on the feedback data received from each respective user predicted to be affected by the catastrophic event, generate an exposure risk set for the common policy provider of the set of users; and transmit, over the one or more network, the exposure risk set generated for the common policy provider to a computing system of the common policy provider.

Description

CROSS REFERENCE TO RELATED APPLICATION This application is a continuation of U.S. patent application Ser. No. 18/432,924, filed on Feb. 5, 2024; which is a continuation of U.S. patent application Ser. No. 17/500,689, filed on Oct. 13, 2021, now U.S. Pat. No. 11,948,201, issued Apr. 2, 2024; all of the aforementioned priority applications being hereby incorporated by reference in their respective entireties. BACKGROUND Catastrophic event preparedness is typically left to affected individuals within predicted or observed event areas. Generalities regarding the manner of preparedness continue to result in high damage costs, loss of life, and inadequate mitigation on a collective basis with little to no individualized preparedness guidance, and for certain catastrophic events, imprecise predictions regarding localized severity. Additionally, the insurance industry is inherently reactive with regard to processing claims, with insurance companies typically awaiting claim events and resultant claim filings prior to performing investigative processes. Accordingly, the insurance industry is plagued by rampant fraud that effectively increases premium costs for all policy holders. The investigative processes themselves are also typically manual and inefficient, with investigators and even law enforcement being tasked with identifying fraudulent behavior long after a claim event, enabling perpetrators of insurance fraud to plan carefully and then cover their tracks prior to making a fraudulent claim. BRIEF DESCRIPTION OF THE DRAWINGS The disclosure herein is illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings in which like reference numerals refer to similar elements, and in which: FIG. 1 is a block diagram illustrating an example computing system implementing targeted event monitoring, alert, loss mitigation, and fraud detection techniques, in accordance with examples described herein; FIG. 2 is a block diagram illustrating an example computing device executing one or more service applications for communicating with a computing system, according to examples described herein; FIGS. 3A and 3B are example graphical user interfaces (GUIs) showing targeted content being presented to a user, according to various examples; FIG. 4A is a flow chart describing an example method of predicting a claim event affecting a set of users, according to various examples; FIG. 4B is a flow chart describing an example method of providing individualized loss mitigation content to users that are predicted to be affected by an event, according to examples described herein; FIGS. 5A and 5B are GUIs presenting an individualized dashboard of an event, according to various examples; FIG. 6 is a flow chart describing an example method of dynamically interacting with a user during an event, according to various examples; FIGS. 7A and 7B are example GUIs presenting interactive content for a user subsequent to an event, according to various examples; FIG. 8A is a flow chart describing an example method of dynamic interaction with a user subsequent to an event, according to various examples; FIG. 8B is a flow chart describing an example method corroborating first notice of loss (FNOL) information from a claimant subsequent to an event, according to various examples; FIG. 8C is a flow chart describing an example method of executing fraud pattern matching utilizing historical data, according to various examples; FIGS. 9A-9X illustrate a series of interactive GUIs that enable a claimant to initiate a claim, according to examples; FIG. 10A is a flow chart describing an example method of contextual information gathering and corroboration following a vehicle incident, according to various examples; FIG. 10B is a flow chart describing an example method of contextual information gathering and corroboration following a personal injury event, according to various examples; FIGS. 11A-E illustrate example claim interfaces generated for policy providers based on claim, according to various examples provided herein; FIG. 12 is a flow chart describing an example method of executing an incident simulation based on party inputs, in accordance with examples described herein; and FIG. 13 is a block diagram that illustrates a computer system upon which examples described herein may be implemented. DETAILED DESCRIPTION A computing system can provide an integrated claims intelligence platform for policy holders and policy providers that leverages various combinations of technologies in machine learning, artificial intelligence, data augmentation, convolutional neural networks, and/or recursive modeling to provide highly predictive and individualized loss prevention and mitigation services, as well as highly detailed and accurate contextual information gathering, corroboration, and claim processing for both policy holders and policy providers. In various implementations, the system can integrate with various third-party d