IP Library › Granted Patent US 12,614,234
Granted Patent B2
US 12,614,234 · App. 18/204,625 · Granted Apr 28, 2026

Ground truth insurance database

Inventors: Brian Mark Fields (Phoenix, AZ); Nathan L. Tofte (Downs, IL); Joseph Robert Brannan (Bloomington, IL); Vicki King (Bloomington, IL); Justin Davis (Bloomington, IL)
Assignee: STATE FARM MUTUAL AUTOMOBILE INSURANCE
G06Q40/08H04L51/02G06F40/40G06Q50/26
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,614,234
App. No.
18/204,625
Granted
Apr 28, 2026
Kind
B2
Abstract

The following relates generally to building a ground truth insurance database. In some embodiments, one or more processors: (1) receive potential insurance database information comprising (i) insurance company application (app) information, (ii) anonymized insurance claim information, (iii) police report information, and/or (iv) auxiliary information; (2) retrieve, from an insurance ground truth insurance database, existing ground truth insurance information by querying the ground truth database based upon the potential insurance database information; (3) determine if the potential insurance database information should be added to the insurance ground truth database by comparing the potential insurance database information to the existing ground truth insurance information; and/or (4) if the potential insurance database information should be added to the insurance ground truth database, add the potential insurance database information to the insurance ground truth database.

Claims (146)

1 . A computer system for building a ground truth insurance database via a generative pre-trained transformer with a multi-head self-attention mechanism, the computer system comprising one or more processors configured to:

receive potential insurance database information, wherein the potential insurance database information comprises: (i) insurance company application (app) information, (ii) anonymized insurance claim information, and/or (iii) police report information;

retrieve, from the ground truth insurance database, existing ground truth insurance information by querying the ground truth insurance database based upon the potential insurance database information;

determine if the potential insurance database information should be added to the ground truth insurance database by comparing the potential insurance database information to the existing ground truth insurance information by:

generating, via the generative pre-trained transformer: (i) a first summary document summarizing the potential insurance database information, and (ii) a second summary document summarizing the existing ground truth insurance information, wherein the generative pre-trained transformer is configured to generate the first summary document by, with the multi-head self-attention mechanism: (i) receiving, as an input, tokens included in the potential insurance database information, and (ii) performing, in parallel:

(a) generating a query vector, a key vector, and a value vector for each token,

(b) generating normalized weights based upon similarities between query vectors and key vectors, and

(c) generating final vectors based upon (i) the normalized weights and (ii) the value vectors;

generating the first summary document based upon the final vectors;

sending the first and second summary documents to an administrator computing device;

receiving, from the administrator computing device, a selection of the potential insurance database information or the existing ground truth insurance information; and

determining to add the potential insurance database information to the ground truth insurance database if the selection indicates the potential insurance database information; and

if the potential insurance database information should be added to the ground truth insurance database, add the potential insurance database information to the ground truth insurance database.

2 . The computer system of claim 1 , wherein the one or more processors are further configured to perform the comparing of the potential insurance database information to the existing ground truth insurance information further by:

generating, via an artificial intelligence (AI) and/or machine learning (ML) chatbot, a comparison document indicating at least one difference between the potential insurance database information and the existing ground truth insurance information;

sending the comparison document to the administrator computing device;

receiving, from the administrator computing device, a selection of the potential insurance database information or the existing ground truth insurance information; and

determining to add the potential insurance database information to the ground truth insurance database if the selection indicates the potential insurance database information.

3 . The computer system of claim 2 , wherein the one or more processors are further configured to perform the generating the comparison document by, via the AI or ML chatbot:

generating a template including the existing ground truth insurance information; and

highlighting at least a portion of the template to indicate the at least one difference between the potential insurance database information and the existing ground truth insurance information.

4 . The computer system of claim 3 , wherein:

the generated comparison further includes: (i) an indication of a source of the potential insurance database information, and/or (ii) an indication of a source of the existing ground truth insurance information; and

the one or more processors are further configured to display, on a display of the administrator computing device, the generated comparison document including (i) the indication of the source of the potential insurance database information, and/or (ii) the indication of the source of the existing ground truth insurance information.

5 . The computer system of claim 2 , wherein the at least one difference comprises a difference in:

a date that an auto accident occurred;

a date that property damage occurred;

a date of a house fire;

vehicle information including vehicle: year, make, model, color, trim level, milage, and/or safety feature information;

an amount paid for an insurance claim;

an amount of a subrogation demand;

a name of a person;

a name of a police officer;

a weather condition on a date of an event of an insurance claim;

if an insurance customer has additional insurance;

insurance policy information of the insurance customer;

a beneficiary of an insurance policy;

a determination of fault in an auto accident;

a record of criminal liability;

items in a home on a date of damage to the home; and/or

personal injury information.

6 . The computer system of claim 1 , wherein the one or more processors are further configured to perform the comparing of the potential insurance database information to the existing ground truth insurance information further by:

comparing a reliability rating of a source of the potential insurance database information to a reliability rating of a source of the existing ground truth insurance information; and/or

comparing (i) a rank of the source of the potential insurance database information from a list of ranked sources to (ii) a rank of a source of the existing ground truth insurance information from the list of ranked sources.

7 . The computer system of claim 1 , wherein the one or more processors are further configured to perform the comparing of the potential insurance database information to the existing ground truth insurance information further by:

determining a type of information of the potential insurance database information;

determining a type of the existing ground truth insurance information;

determining a first reliability rating corresponding to the type of information of the potential database information and a source of the potential insurance database information;

determining a second reliability rating corresponding to the type of information of the existing ground truth insurance information and a source of the existing ground truth insurance information; and

comparing the first reliability rating to the second reliability rating.

8 . The computer system of claim 7 , wherein the one or more processors are further configured to, if the type of information of the potential insurance database information and the type of the existing ground truth insurance information are both imagery information:

determine a higher reliability rating for a police report source than for information from:

a vehicle camera;

a traffic camera;

a camera attached to a building;

an infrastructure device;

a vehicle-to-infrastructure (V2I) device;

a vehicle-to-network (V2N) device;

a vehicle-to-vehicle (V2V) device;

a vehicle-to-pedestrian (V2P) device;

a vehicle-to-device (V2D) device;

a smartwatch;

a smartphone;

a smart home device;

a smart home camera;

an email server;

a weather device;

a government database;

a drone; and/or

a newscast database.

9 . The computer system of claim 1 , wherein the one or more processors are further configured to:

if the potential insurance database information should be added to the ground truth insurance database, further remove the existing ground truth insurance information from the ground truth insurance database.

10 . The computer system of claim 1 , wherein:

the potential insurance database information comprises the insurance company app information, and the insurance company app information comprises a profile of an insurance customer; and

the one or more processors are further configured to receive the insurance company app information from an insurance company app.

11 . The computer system of claim 1 , wherein:

the potential insurance database information comprises the anonymized insurance claim information, and the anonymized insurance claim information includes: a date of a first notice of loss, an amount of an insurance payout, and/or a type of insurance claim.

12 . The computer system of claim 1 , wherein:

the potential insurance database information comprises police report information; and

the police report information includes a name of a police department of the police report, a name of a police officer of the police report, a type of vehicle involved in an accident, imagery information of the accident, a percentage of fault of the accident, imagery information of a home, an identity of a deceased person, and/or an identity of a person filing a police report.

13 . The computer system of claim 1 , wherein the potential insurance database information further comprises information from:

a vehicle camera;

a traffic camera;

a camera attached to a building;

an infrastructure device;

a vehicle-to-infrastructure (V2I) device;

a vehicle-to-network (V2N) device;

a vehicle-to-vehicle (V2V) device;

a vehicle-to-pedestrian (V2P) device;

a vehicle-to-device (V2D) device;

a smartwatch;

a smartphone;

a smart home device;

a smart home camera;

an email server;

a weather device;

a government database;

a drone; and/or

a newscast database.

14 . The computer system of claim 1 , wherein the tokens comprise respective text strings from the potential insurance database information.

15 . A computer-implemented method for building a ground truth insurance database via a generative pre-trained transformer with a multi-head self-attention mechanism, the method comprising:

receiving, via one or more processors, potential insurance database information, wherein the potential insurance database information comprises: (i) insurance company application (app) information, (ii) anonymized insurance claim information, and/or (iii) police report information;

retrieving, via the one or more processors, from the ground truth insurance database, existing ground truth insurance information by querying the ground truth insurance database based upon the potential insurance database information;

determining, via the one or more processors, that the potential insurance database information should be added to the ground truth insurance database by comparing the potential insurance database information to the existing ground truth insurance information by:

generating, via the generative pre-trained transformer: (i) a first summary document summarizing the potential insurance database information, and (ii) a second summary document summarizing the existing ground truth insurance information, wherein the generative pre-trained transformer is configured to generate the first summary document by, with the multi-head self-attention mechanism: (i) receiving, as an input, tokens included in the potential insurance database information, and (ii) performing, in parallel:

(a) generating a query vector, a key vector, and a value vector for each token,

(b) generating normalized weights based upon similarities between query vectors and key vectors, and

(c) generating final vectors based upon (i) the normalized weights and (ii) the value vectors;

generating the first summary document based upon the final vectors;

sending the first and second summary documents to an administrator computing device;

receiving, from the administrator computing device, a selection of the potential insurance database information or the existing ground truth insurance information; and

determining to add the potential insurance database information to the ground truth insurance database if the selection indicates the potential insurance database information; and

in response to the determination that the potential insurance database information should be added to the ground truth insurance database, adding, via the one or more processors, the potential insurance database information to the ground truth insurance database.

16 . The computer-implemented method of claim 15 , wherein the potential insurance database information comprises the police report information, and the method further comprises, via the one or more processors:

with an artificial intelligence (AI) or machine learning (ML) chatbot, requesting the police report information from a police station.

17 . The computer-implemented method of claim 15 , wherein the method further comprises, via the one or more processors:

with an artificial intelligence (AI) or machine learning (ML) chatbot, requesting information from:

(i) a government entity storing death records and/or vehicle registration records, (ii) an entity storing data from a vehicle-to-infrastructure (V2I) device, a vehicle-to-network (V2N) device, a vehicle-to-vehicle (V2V) device, a vehicle-to-pedestrian (V2P) device, and/or a vehicle-to-device (V2D) device, and/or (iii) a news source; and

adding the requested information to the potential insurance database information.

18 . A computer device for building a ground truth insurance database via a generative pre-trained transformer with a multi-head self-attention mechanism, the computer device comprising:

one or more processors; and

one or more memories;

the one or more memories having stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computer device to:

receive potential insurance database information, wherein the potential insurance database information comprises: (i) insurance company application (app) information, (ii) anonymized insurance claim information, and/or (iii) police report information;

retrieve, from the ground truth insurance database, existing ground truth insurance information by querying the ground truth insurance database based upon the potential insurance database information;

determine if the potential insurance database information should be added to the ground truth insurance database by comparing the potential insurance database information to the existing ground truth insurance information by:

generating, via the generative pre-trained transformer: (i) a first summary document summarizing the potential insurance database information, and (ii) a second summary document summarizing the existing ground truth insurance information, wherein the generative pre-trained transformer is configured to generate the first summary document by, with the multi-head self-attention mechanism: (i) receiving, as an input, tokens included in the potential insurance database information, and (ii) performing, in parallel:

(a) generating a query vector, a key vector, and a value vector for each token,

(b) generating normalized weights based upon similarities between query vectors and key vectors, and

(c) generating final vectors based upon (i) the normalized weights and (ii) the value vectors;

generating the first summary document based upon the final vectors;

sending the first and second summary documents to an administrator computing device;

receiving, from the administrator computing device, a selection of the potential insurance database information or the existing ground truth insurance information; and

determining to add the potential insurance database information to the ground truth insurance database if the selection indicates the potential insurance database information; and

if the potential insurance database information should be added to the ground truth insurance database, add the potential insurance database information to the ground truth insurance database.

19 . The computer device of claim 18 , wherein the potential insurance database information comprises the police report information, and wherein the one or more memories having stored thereon computer executable instructions that, when executed by the one or more processors, further cause the computer device to:

with an artificial intelligence (AI) chatbot, prepare a draft communication to request the police report information from a police department;

present the draft communication to an administrator on the administrator computing device;

receive, from the administrator computing device, a final communication, wherein the final communication comprises an edited version of the draft communication edited by the administrator; and

send the final communication to the police department.

20 . The computer device of claim 19 , wherein the draft communication and final communication each comprise an email and/or text message.

21 . The computer device of claim 18 , wherein the one or more memories having stored thereon computer executable instructions that, when executed by the one or more processors, further cause the computer device to perform the querying of the ground truth insurance database based upon an insurance claim identifier, wherein the insurance claim identifier comprises an insurance claim number.

22 . The computer device of claim 18 , wherein the one or more memories having stored thereon computer executable instructions that, when executed by the one or more processors, further cause the computer device to:

use a natural language processing algorithm (NLP) to determine a word or phrase from the potential insurance information; and

perform the querying of the ground truth insurance database by querying the ground truth insurance database based upon the word or phrase.

23 . The computer device of claim 19 , wherein the AI chatbot comprises: a generative AI chatbot, and/or a deep learning algorithm.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 1, 2023
From: FIELDS, BRIAN MARK; TOFTE, NATHAN L.; BRANNAN, JOSEPH ROBERT; KING, VICKI; DAVIS, JUSTIN
To: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY
Reel/Frame 063830/0195 →
Continuity (10)
Provisional Application 63455154 · Mar 28, 2023
Provisional Application 63453285 · Mar 20, 2023
Provisional Application 63452035 · Mar 14, 2023
Provisional Application 63450837 · Mar 8, 2023
Provisional Application 63447757 · Feb 23, 2023
Provisional Application 63447745 · Feb 23, 2023
Provisional Application 63447391 · Feb 22, 2023
Provisional Application 63446952 · Feb 20, 2023
Provisional Application 63446941 · Feb 20, 2023
Related Publication 20240281890A1 · Aug 22, 2024
References Cited (234)
US 7698342B1 · Evans et al. · 2010 [cited by applicant]
US 8095393B2 · Seifert et al. · 2012 [cited by applicant]
US 8346563B1 · Hjelm et al. · 2013 [cited by applicant]
US 9830748B2 · Rosenbaum · 2017 [cited by applicant]
US 9990782B2 · Rosenbaum · 2018 [cited by applicant]
US 10043217B1 · Bolden et al. · 2018 [cited by applicant]
US 10055793B1 · Call et al. · 2018 [cited by applicant]
US 10181159B1 · Allen et al. · 2019 [cited by applicant]
US 10217068B1 · Davis et al. · 2019 [cited by applicant]
US 10229394B1 · Davis et al. · 2019 [cited by applicant]
US 10269190B2 · Rosenbaum · 2019 [cited by applicant]
US 10387966B1 · Shah et al. · 2019 [cited by applicant]
US 10467824B2 · Rosenbaum · 2019 [cited by applicant]
US 10482554B1 · Vukich et al. · 2019 [cited by applicant]
US 10497250B1 · Hayward et al. · 2019 [cited by applicant]
US 10535104B1 · Mitchell et al. · 2020 [cited by applicant]
US 10579971B1 · Davis et al. · 2020 [cited by applicant]
US 10635751B1 · Relangi et al. · 2020 [cited by applicant]
US 10679296B1 · Devereaux et al. · 2020 [cited by applicant]
US 10769953B1 · Salles et al. · 2020 [cited by applicant]
US 11038821B1 · Harding et al. · 2021 [cited by applicant]
US 11087404B1 · Devereaux et al. · 2021 [cited by applicant]
US 11127081B1 · Kullman et al. · 2021 [cited by applicant]
US 11227452B2 · Rosenbaum · 2022 [cited by applicant]
US 11238506B1 · Tomlinson et al. · 2022 [cited by applicant]
US 11250515B1 · Feiteira et al. · 2022 [cited by applicant]
US 11407410B2 · Rosenbaum · 2022 [cited by applicant]
US 11438283B1 · White et al. · 2022 [cited by applicant]
US 11518391B1 · Sanchez · 2022 [cited by examiner]
US 11524707B2 · Rosenbaum · 2022 [cited by applicant]
US 11544807B1 · Breitweiser et al. · 2023 [cited by applicant]
US 11594083B1 · Rosenbaum · 2023 [cited by applicant]
US 11669907B1 · Behrens et al. · 2023 [cited by applicant]
US 11693726B2 · Lozano et al. · 2023 [cited by applicant]
US 11720903B1 · Henryson et al. · 2023 [cited by applicant]
US 11757807B2 · Bhardwaj et al. · 2023 [cited by applicant]
US 11783421B2 · Huls · 2023 [cited by applicant]
US 11790296B1 · Henryson et al. · 2023 [cited by applicant]
US 11818111B1 · Debolt · 2023 [cited by applicant]
US 11836805B1 · Culbertson et al. · 2023 [cited by applicant]
US 11837004B1 · Agrahari et al. · 2023 [cited by applicant]
US 11922515B1 · Lombard et al. · 2024 [cited by applicant]
US 12087152B1 · Buentello et al. · 2024 [cited by applicant]
US 12217606B1 · Cheng et al. · 2025 [cited by applicant]
US 12236377B2 · Sohum et al. · 2025 [cited by applicant]
US 12248993B2 · Brannan et al. · 2025 [cited by applicant]
US 20010027403A1 · Peterson et al. · 2001 [cited by applicant]
US 20010037265A1 · Kleinberg · 2001 [cited by applicant]
US 20020002475A1 · Freedman et al. · 2002 [cited by applicant]
US 20020112011A1 · Washington · 2002 [cited by applicant]
US 20030028448A1 · Joseph et al. · 2003 [cited by applicant]
US 20060212566A1 · Boujard et al. · 2006 [cited by applicant]
US 20080056473A1 · Kent et al. · 2008 [cited by applicant]
US 20090125320A1 · Bickett · 2009 [cited by applicant]
US 20090240531A1 · Hilborn · 2009 [cited by applicant]
US 20090287509A1 · Basak et al. · 2009 [cited by applicant]
US 20100145734A1 · Becerra et al. · 2010 [cited by applicant]
US 20110119574A1 · Rogers · 2011 [cited by examiner]
US 20110295623A1 · Behringer et al. · 2011 [cited by applicant]
US 20110313794A1 · Feeney · 2011 [cited by applicant]
US 20120101852A1 · Albert · 2012 [cited by applicant]
US 20120124485A1 · Scherpa et al. · 2012 [cited by applicant]
US 20120143634A1 · Beyda et al. · 2012 [cited by applicant]
US 20120303390A1 · Brook et al. · 2012 [cited by applicant]
US 20130204619A1 · Berman et al. · 2013 [cited by applicant]
US 20130218603A1 · Hagelstein et al. · 2013 [cited by applicant]
US 20130226624A1 · Blessman et al. · 2013 [cited by applicant]
US 20140094991A1 · Bouillet · 2014 [cited by examiner]
US 20140100892A1 · Collopy et al. · 2014 [cited by applicant]
US 20140222469A1 · Stahl et al. · 2014 [cited by applicant]
US 20140358731A1 · Itte et al. · 2014 [cited by applicant]
US 20140379385A1 · Duncan et al. · 2014 [cited by applicant]
US 20150170288A1 · Harton et al. · 2015 [cited by applicant]
US 20150213556A1 · Haller, Jr. · 2015 [cited by applicant]
US 20150338235A1 · Schmidt et al. · 2015 [cited by applicant]
US 20150339759A1 · Pope et al. · 2015 [cited by applicant]
US 20160041069A1 · Huang et al. · 2016 [cited by applicant]
US 20160071217A1 · Edwards et al. · 2016 [cited by applicant]
US 20160086231A1 · Darey · 2016 [cited by applicant]
US 20160238397A1 · Caira et al. · 2016 [cited by applicant]
US 20160273181A1 · Smith · 2016 [cited by applicant]
US 20170004508A1 · Mansfield et al. · 2017 [cited by applicant]
US 20170060694A1 · Makhov et al. · 2017 [cited by applicant]
US 20170103346A1 · Bodell et al. · 2017 [cited by applicant]
US 20170132643A1 · Sagade · 2017 [cited by examiner]
US 20170132666A1 · Slavin · 2017 [cited by applicant]
US 20170191848A1 · Jones · 2017 [cited by applicant]
US 20180047288A1 · Cordell et al. · 2018 [cited by applicant]
US 20180075538A1 · Konrardy et al. · 2018 [cited by applicant]
US 20180082683A1 · Chen et al. · 2018 [cited by applicant]
US 20180173999A1 · Renard · 2018 [cited by applicant]
US 20180293483A1 · Abramson et al. · 2018 [cited by applicant]
US 20180293660A1 · Rakshe et al. · 2018 [cited by applicant]
US 20180334176A1 · Park · 2018 [cited by applicant]
US 20190037077A1 · Konig et al. · 2019 [cited by applicant]
US 20190095822A1 · Rugel et al. · 2019 [cited by applicant]
US 20190114715A1 · Hessinger et al. · 2019 [cited by applicant]
US 20190122121A1 · Yu · 2019 [cited by applicant]
US 20190306327A1 · Matysiak et al. · 2019 [cited by applicant]
US 20190332661A1 · Halprin Limor · 2019 [cited by examiner]
US 20190391827A1 · Simanovich et al. · 2019 [cited by applicant]
US 20200019893A1 · Lu · 2020 [cited by applicant]
US 20200042649A1 · Bakis et al. · 2020 [cited by applicant]
US 20200104876A1 · Chintakindi et al. · 2020 [cited by applicant]
US 20200143481A1 · Brown et al. · 2020 [cited by applicant]
US 20200154170A1 · Wu et al. · 2020 [cited by applicant]
US 20200167134A1 · Dey et al. · 2020 [cited by applicant]
US 20200210490A1 · Hutchins · 2020 [cited by applicant]
US 20200274962A1 · Martin et al. · 2020 [cited by applicant]
US 20200285225A1 · Lankehanumaiah et al. · 2020 [cited by applicant]
US 20200339160A1 · Rosenbaum · 2020 [cited by applicant]
US 20210064932A1 · Wang · 2021 [cited by examiner]
US 20210073330A1 · Inagaki et al. · 2021 [cited by applicant]
US 20210117923A1 · Gray et al. · 2021 [cited by applicant]
US 20210152496A1 · Kim et al. · 2021 [cited by applicant]
US 20210200950A1 · Basu et al. · 2021 [cited by applicant]
US 20210203784A1 · Konig et al. · 2021 [cited by applicant]
US 20210256616A1 · Hayward et al. · 2021 [cited by applicant]
US 20210271820A1 · Raghupatruni et al. · 2021 [cited by applicant]
US 20210273892A1 · Rakshit · 2021 [cited by applicant]
US 20210295203A1 · Liao et al. · 2021 [cited by applicant]
US 20210350357A1 · Lafontaine · 2021 [cited by applicant]
US 20210357771A1 · Flowers et al. · 2021 [cited by applicant]
US 20210357790A1 · Volkov et al. · 2021 [cited by applicant]
US 20210365955A1 · Galante et al. · 2021 [cited by applicant]
US 20210366048A1 · Westhues et al. · 2021 [cited by applicant]
US 20210374092A1 · Sahay · 2021 [cited by applicant]
US 20210390950A1 · Kumar et al. · 2021 [cited by applicant]
US 20210406938A1 · Thakral · 2021 [cited by applicant]
US 20220004630A1 · Almukaynizi · 2022 [cited by examiner]
US 20220019496A1 · Lozano et al. · 2022 [cited by applicant]
US 20220091957A1 · Szczepanik et al. · 2022 [cited by applicant]
US 20220092893A1 · Rosenbaum · 2022 [cited by applicant]
US 20220094789A1 · Lau et al. · 2022 [cited by applicant]
US 20220114594A1 · Nunes et al. · 2022 [cited by applicant]
US 20220136847A1 · Higuchi et al. · 2022 [cited by applicant]
US 20220176971A1 · Nordh · 2022 [cited by applicant]
US 20220198531A1 · Cleaver et al. · 2022 [cited by applicant]
US 20220261535A1 · Madaan · 2022 [cited by examiner]
US 20220269583A1 · Plawecki · 2022 [cited by applicant]
US 20220279014A1 · Stokes et al. · 2022 [cited by applicant]
US 20220293107A1 · Leaman et al. · 2022 [cited by applicant]
US 20220300993A1 · Chaudhry et al. · 2022 [cited by applicant]
US 20220308943A1 · Srinivasan et al. · 2022 [cited by applicant]
US 20220340148A1 · Rosenbaum · 2022 [cited by applicant]
US 20220366459A1 · Vieyra · 2022 [cited by applicant]
US 20230005070A1 · Nguyen et al. · 2023 [cited by applicant]
US 20230017739A1 · Feldman et al. · 2023 [cited by applicant]
US 20230023869A1 · Ganesan et al. · 2023 [cited by applicant]
US 20230060300A1 · Rosenbaum · 2023 [cited by applicant]
US 20230064816A1 · Matsuoka et al. · 2023 [cited by applicant]
US 20230105564A1 · Breitweiser et al. · 2023 [cited by applicant]
US 20230108454A1 · Gidwaney et al. · 2023 [cited by applicant]
US 20230110941A1 · Makhija et al. · 2023 [cited by applicant]
US 20230116639A1 · Patt et al. · 2023 [cited by applicant]
US 20230140931A1 · Anderson et al. · 2023 [cited by applicant]
US 20230141853A1 · Vu et al. · 2023 [cited by applicant]
US 20230244938A1 · Wei et al. · 2023 [cited by applicant]
US 20230259821A1 · Travalini et al. · 2023 [cited by applicant]
US 20230267512A1 · Isackson et al. · 2023 [cited by applicant]
US 20230267694A1 · Breitweiser et al. · 2023 [cited by applicant]
US 20230290502A1 · Zhi · 2023 [cited by examiner]
US 20230298567A1 · Tan et al. · 2023 [cited by applicant]
US 20230316412A1 · Behrens et al. · 2023 [cited by applicant]
US 20230343149A1 · Volos et al. · 2023 [cited by applicant]
US 20230385939A1 · Tsuchiyma et al. · 2023 [cited by applicant]
US 20230410801A1 · Mishra · 2023 [cited by applicant]
US 20240073219A1 · Maizels et al. · 2024 [cited by applicant]
US 20240102814A1 · Karri et al. · 2024 [cited by applicant]
US 20240119424A1 · Lofvers et al. · 2024 [cited by applicant]
US 20240167864A1 · Donovan et al. · 2024 [cited by applicant]
US 20240168611A1 · Pham et al. · 2024 [cited by applicant]
US 20240248920A1 · Qiao et al. · 2024 [cited by applicant]
US 20240249557A1 · Chavali · 2024 [cited by applicant]
US 20240256780A1 · Douglas et al. · 2024 [cited by applicant]
US 20240281888A1 · Fields et al. · 2024 [cited by applicant]
US 20240281889A1 · Fields et al. · 2024 [cited by applicant]
US 20240281891A1 · Fields et al. · 2024 [cited by applicant]
US 20240289362A1 · Williams et al. · 2024 [cited by applicant]
US 20240289596A1 · Williams et al. · 2024 [cited by applicant]
US 20240289851A1 · Williams et al. · 2024 [cited by applicant]
US 20240291777A1 · Fields et al. · 2024 [cited by applicant]
US 20240303745A1 · Fields et al. · 2024 [cited by applicant]
US 20240311271A1 · Fields et al. · 2024 [cited by applicant]
US 20240311921A1 · Fields et al. · 2024 [cited by applicant]
US 20240311922A1 · Fields et al. · 2024 [cited by applicant]
US 20240328410A1 · Williams et al. · 2024 [cited by applicant]
US 20240331047A1 · Williams et al. · 2024 [cited by applicant]
US 20240331068A1 · Williams et al. · 2024 [cited by applicant]
US 20240362686A1 · Williams et al. · 2024 [cited by applicant]
US 20240371367A1 · Churgin · 2024 [cited by examiner]
US 20240371376A1 · Bohl et al. · 2024 [cited by applicant]
US 20240395138A1 · Brannan et al. · 2024 [cited by applicant]
US 20240395145A1 · Brannan et al. · 2024 [cited by applicant]
US 20240403596A1 · Brannan et al. · 2024 [cited by applicant]
US 20240412294A1 · Brannan et al. · 2024 [cited by applicant]
US 20240414105A1 · Brannan et al. · 2024 [cited by applicant]
US 20250013555A1 · Papadopoulos et al. · 2025 [cited by applicant]
CA 3227939A1 · 2023 [cited by applicant]
CN 112164391A · 2021 [cited by applicant]
EP 2946168A1 · 2015 [cited by applicant]
EP 3239686A1 · 2017 [cited by applicant]
EP 3578433B1 · 2020 [cited by applicant]
EP 3730375B1 · 2021 [cited by applicant]
EP 3960576A1 · 2022 [cited by applicant]
EP 4190659A1 · 2023 [cited by applicant]
EP 4190660A1 · 2023 [cited by applicant]
IN 201741025968 · 2017 [cited by applicant]
KR 102148616B1 · 2020 [cited by applicant]
WO 2013059620A2 · 2013 [cited by applicant]
WO 2023021162A2 · 2023 [cited by applicant]
Anonymous, Roots Automation Introduces InsurGPT - the World's Most Advanced Generative AI Model for Insurance. Retrieved from the Internet at: https://ffnews.com/newsarticle/roots-automation-introduces-insurgpt-the-worl… [cited by applicant]
Introducing Agent M—a powerful Large Language model or ChatGPT based Master Agent developer framework, powered by Floatbot platform, that lets you create multiple application—specific LLM-based Agent(s). Retrieved from … [cited by applicant]
Isenberg, The Compliance Tasks ChatGPT Can (and Can't) Handle, Ignites (published Apr. 3, 2023). [cited by applicant]
Morelli, Will ChatGPT, artificial intelligence replace financial professionals any time soon?, Insurance NewsNet. Retrieved from the Internet at: <https://insurancenewsnet.com/innarticle/will-chatgpt-artificial-intellig… [cited by applicant]
Morris, Morgan Stanley Developing Chatbot with OpenAI, Ignites (published Mar. 15, 2023). [cited by applicant]
Munk, Will AI models like ChatGPT take your insurance job?, Life Annuity Speciality (published Mar. 7, 2023). [cited by applicant]
Rengachary et al., ChatGPT: A Conversation About Underwriting and Life Insurance. Retrieved from the internet at: https://www.coverager.com/chatgpt-a-conversation-about-underwriting-and-life-insurance/ (published Apr. 3… [cited by applicant]
Smith, Insurer Zurich experiments with ChatGPT for claims and data mining, Financial Times (published Mar. 24, 2023). [cited by applicant]
Tuohy, What ChatGPT's Chores May Look Like in Life Insurance Industry, Life Annuity Specialist (published Apr. 21, 2023). [cited by applicant]
Wilson, Should Financial Services Companies Consider Open AI?, LIMRA.com MarketFacts (published Mar. 2023). [cited by applicant]
Dickson, How to create a private ChatGPT that interacts with your local documents, TechTalks. Retrieved from the Internet at: <URL:https://bdtechtalks.com/2023/06/01/create-privategpt-local-llm/> (Jun. 2023). [cited by applicant]
OpenPR Worldwide Public Relations, Press release, “Floatbot.AI Unveils Revolutionary Agent M—Generative AI (LLM or ChatGPT) Based Master Agent developer framework,” Web page downloaded from Internet at <https://www.open… [cited by applicant]
The Future of Car Insurance #2: How AI Is Transforming Auto Insurance for Companies and Drivers, Brogan Woodburn, Rashawn Mitchner, dated Jun. 22, 2023. (Year: 2023). [cited by applicant]
STIC EIC Search Report for U.S. Appl. No. 18/196,691 (Year: 2024). [cited by applicant]
Wang et al., Transfer learning-based query classification for intelligent building information spoken dialogue. Automation in Construction. Sep. 1, 2022; 141:104403. (Year: 2022). [cited by applicant]
A. Wang N, Issa RR, Anumba CJ. Transfer learning-based query classification for intelligent building information spoken dialogue. Automation in Construction. Sep. 1, 2022; 141:104403. (Year: 2022). [cited by applicant]
ip.com NPL Search History (2025). [cited by applicant]
Mleczko, K. (2021). Chatbot as a tool for knowledge sharing in the maintenance and repair processes. Multidisciplinary Aspects of Production Engineering, 4(1), 499-508. (Year: 2021). [cited by applicant]
“Encrypt Team,” “ChatGPT—AI Chat bot—A Complete Guide,” www.theencrypt.com 2022 (Year: 2022). [cited by applicant]
Hossen et al., Controlling home appliances adopting chatbot using machine learning approach. In International Conference on Intelligent Computing & Optimization, pp. 253-264, Springer International Publishing (Oct. 2022… [cited by applicant]
Jadhav et al., “Design and Development of Chatbot Based on Reinforcement Learning,” Chapter 12, https://doi.org/10.1002/9781119861850.ch12 2022 (Year: 2022). [cited by applicant]
Sankaranarayanan et al., Flood prediction based on weather parameters using deep learning, Journal of Water and Climate Change, 2020 (Year: 2020). [cited by applicant]
Zhang et al. (“DIALOGPT : Large-Scale Generative Pre-training for Conversational Response Generation”, A collaboration between Microsoft Research and Microsoft Dynamics 365 Al Research, pp. 270-278, Jul. 5-Jul. 10, 2020… [cited by applicant]