Granted Patent B2

US 12,737,819 · App. 18/809,127 · Granted Sep 15, 2026

Inventors: Justin Lewis-Weber (Stanford, CA); Theo Patt (Stanford, CA)

Assignee: Assured Insurance Technologies, Inc.

G06Q40/08G06Q30/015

Abstract

Claims (40)

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 perform operations that include:

training one or more injury assistance models to provide, based on incident data provided by users involved in injury events, individualized injury assistance to the users, the training being based on claim information obtained from a plurality of settled claims, the training including;

(i) identifying, from the claim information, each of (a) injury inputs received from claimants, (b) recovery information for each claimant, (c) initial reserve estimates determined for the claimants based on their injury inputs, and (d) finalized settlement offers provided to claimants;

(ii) for each settled claim of the plurality of settled claims, determining a discrepancy between an initial reserve estimate determined for a claimant of the settled claim, and a finalized settlement offer provided to the claimant; and

(iii) tuning the one or more injury assistance models based on the determined discrepancies;

receiving, over one or more networks, incident data identifying an injury to a user; and

executing the one or more injury assistance models on the incident data to provide individualized injury assistance to the user while the user recovers from the injury, wherein the executing generates a set of predictive determinations for a treatment plan for the user's recovery; and

based on the predictive determinations, performing point-in-time check-ins with the user.

2 . The computing system of claim 1 , wherein the operations include:

simulating an event that caused the injury to the user based at least in part on the incident data provided by the user; and

corroborating the injury to the user based on the simulation.

3 . The computing system of claim 2 , wherein the operations include:

verifying recovery update information provided by the user by accessing medical data of the user and verifying whether the recovery update information matches the medical data.

4 . A non-transitory computer readable medium storing instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations that include:

training one or more injury assistance models to provide, based on incident data provided by users involved in injury events, individualized injury assistance to the users, the training being based on claim information obtained from a plurality of settled claims, the training including:

(i) identifying, from the claim information, each of (a) injury inputs received from claimants, (b) recovery information for each claimant, (c) initial reserve estimates determined for the claimants based on their injury inputs, and (d) finalized settlement offers provided to claimants;

(ii) for each settled claim of the plurality of settled claims, determining a discrepancy between an initial reserve estimate determined for a claimant of the settled claim, and a finalized settlement offer provided to the claimant; and

(iii) tuning the one or more injury assistance models based on the determined discrepancies;

receiving, over one or more networks, incident data identifying an injury to a user; and

executing the one or more injury assistance models on the incident data to provide individualized injury assistance to the user while the user recovers from the injury, wherein the executing generates a set of predictive determinations for a treatment plan for the user's recovery; and

based on the predictive determinations, performing point-in-time check-ins with the user.

5 . The non-transitory computer readable medium of claim 4 , wherein the operations include:

simulating an event that caused the injury to the user based at least in part on the incident data provided by the user; and

corroborating the injury to the user based on the simulation.

6 . The non-transitory computer readable medium of claim 5 , wherein the operations include:

verifying recovery update information provided by the user by accessing medical data of the user and verifying whether the recovery update information matches the medical data.

7 . A computer-implemented method of providing automated injury assistance, the method being performed by one or more processors and comprising:

training one or more injury assistance models to provide, based on incident data provided by users involved in injury events individualized injury assistance to the users, the training being based on claim information obtained from a plurality of settled claims, the training including:

(i) identifying, from the claim information, each of (a) injury inputs received from claimants, (b) recovery information for each claimant, (c) initial reserve estimates determined for the claimants based on their injury inputs, and (d) finalized settlement offers provided to claimants;

(ii) for each settled claim of the plurality of settled claims, determining a discrepancy between an initial reserve estimate determined for a claimant of the settled claim, and a finalized settlement offer provided to the claimant; and

(iii) tuning the one or more injury assistance models based on the determined discrepancies;

receiving, over one or more networks, incident data identifying an injury to a user; and

executing the one or more injury assistance models on the incident data to provide individualized injury assistance to the user while the user recovers from the injury, wherein the executing generates a set of predictive determinations for a treatment plan for the user's recovery; and

based on the predictive determinations, performing point-in-time check-ins with the user.

8 . The method of claim 7 , wherein the method includes:

simulating an event that caused the injury to the user based at least in part on the incident data provided by the user; and

corroborating the injury to the user based on the simulation.

Continuity (1)

References Cited (140)