公开(公告)号：US11610074B1

公开(公告)日：2023-03-21

申请号：US16937318

申请日：2020-07-23

Applicant: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

Inventor： He Yang ,  Bradley A. Sliz ,  Carlee A. Clymer ,  Jennifer Malia Andrus

IPC: G06K9/62 ,  G06F16/583 ,  G06Q40/08 ,  G06N3/08

Abstract: In a computer-implemented method and associated tangible non-transitory computer-readable medium, an image of a damaged vehicle may be analyzed to generate a repair estimate. A dataset populated with digital images of damaged vehicles and associated claim data may be used to train a deep learning neural network to learn damaged vehicle image characteristics that are predictive of claim data characteristics, and a predictive similarity model may be generated. Using the predictive similarity model, one or more similarity scores may be generated for a digital image of a newly damaged vehicle, indicating its similarity to one or more digital images of damaged vehicles with known damage level, repair time, and/or repair cost. A repair estimate may be generated for the newly damaged vehicle based on the claim data associated with images that are most similar to the image of the newly damaged vehicle.

公开(公告)号：US12008658B2

公开(公告)日：2024-06-11

申请号：US18110510

申请日：2023-02-16

Applicant: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

Inventor： He Yang ,  Bradley A. Sliz ,  Carlee A. Clymer ,  Jennifer Malia Andrus

IPC: G06Q40/08 ,  G06F16/583 ,  G06F18/214 ,  G06F18/22 ,  G06N3/08 ,  G06V10/74 ,  G06V10/82

CPC classification number: G06Q40/08 ,  G06F16/583 ,  G06F18/214 ,  G06F18/22 ,  G06N3/08 ,  G06V10/761 ,  G06V10/82 ,  G06V2201/08

Abstract: In a computer-implemented method and associated tangible non-transitory computer-readable medium, an image of a damaged vehicle may be analyzed to generate a repair estimate. A dataset populated with digital images of damaged vehicles and associated claim data may be used to train a deep learning neural network to learn damaged vehicle image characteristics that are predictive of claim data characteristics, and a predictive similarity model may be generated. Using the predictive similarity model, one or more similarity scores may be generated for a digital image of a newly damaged vehicle, indicating its similarity to one or more digital images of damaged vehicles with known damage level, repair time, and/or repair cost. A repair estimate may be generated for the newly damaged vehicle based on the claim data associated with images that are most similar to the image of the newly damaged vehicle.

公开(公告)号：US10762385B1

公开(公告)日：2020-09-01

申请号：US16023414

申请日：2018-06-29

Applicant: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

Inventor： He Yang ,  Bradley A. Sliz ,  Carlee A. Clymer ,  Jennifer Malia Andrus

IPC: G06K9/00 ,  G06K9/62 ,  G06N3/08 ,  G06Q40/08 ,  G06F16/583

Abstract: In a computer-implemented method and associated tangible non-transitory computer-readable medium, an image of a damaged vehicle may be analyzed to generate a repair estimate. A dataset populated with digital images of damaged vehicles and associated claim data may be used to train a deep learning neural network to learn damaged vehicle image characteristics that are predictive of claim data characteristics, and a predictive similarity model may be generated. Using the predictive similarity model, one or more similarity scores may be generated for a digital image of a newly damaged vehicle, indicating its similarity to one or more digital images of damaged vehicles with known damage level, repair time, and/or repair cost. A repair estimate may be generated for the newly damaged vehicle based on the claim data associated with images that are most similar to the image of the newly damaged vehicle.

公开(公告)号：US20240289891A1

公开(公告)日：2024-08-29

申请号：US18658330

申请日：2024-05-08

Applicant: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

Inventor： He Yang ,  Bradley A. Sliz ,  Carlee A. Clymer ,  Jennifer Malia Andrus

IPC: G06Q40/08 ,  G06F16/583 ,  G06F18/214 ,  G06F18/22 ,  G06N3/08 ,  G06V10/74 ,  G06V10/82

CPC classification number: G06Q40/08 ,  G06F16/583 ,  G06F18/214 ,  G06F18/22 ,  G06N3/08 ,  G06V10/761 ,  G06V10/82 ,  G06V2201/08

Abstract: In a computer-implemented method and associated tangible non-transitory computer-readable medium, an image of a damaged vehicle may be analyzed to generate a repair estimate. A dataset populated with digital images of damaged vehicles and associated claim data may be used to train a deep learning neural network to learn damaged vehicle image characteristics that are predictive of claim data characteristics, and a predictive similarity model may be generated. Using the predictive similarity model, one or more similarity scores may be generated for a digital image of a newly damaged vehicle, indicating its similarity to one or more digital images of damaged vehicles with known damage level, repair time, and/or repair cost. A repair estimate may be generated for the newly damaged vehicle based on the claim data associated with images that are most similar to the image of the newly damaged vehicle.

公开(公告)号：US20230135121A1

公开(公告)日：2023-05-04

申请号：US18091702

申请日：2022-12-30

Applicant: State Farm Mutual Automobile Insurance Company

Inventor： Carlee A. Clymer ,  Gary Foreman ,  Ronald R. Duehr ,  Denson Smith ,  Vincent M. Hummel ,  Bradley J Walder ,  Chad Mychal Hirst ,  Justin Devore ,  Shane Tomlinson ,  David A Pluimer ,  Pavan Kumar Bhagavatula ,  John Westhues ,  Tracey Leigh Knorr ,  Erin E. Miller ,  Joshua T. Monk ,  Aaron Ames ,  John G. McConkey ,  Michael Cicilio Fresquez ,  Himanshu Chhita ,  Jason Beckman ,  Douglas A. Graff ,  Michele Wittman ,  Alexis Cates ,  Stephen Young ,  Rajesh Panicker ,  Yohan Santos ,  Stephen Wilson ,  Carrie A Read ,  Michael Brown ,  Robin A Rose

IPC: G06Q40/08 ,  G06N7/01 ,  G07C5/08

Abstract: A method of identifying a vehicle total loss claim includes retrieving a plurality of historical vehicle records, labeling the records as repaired or total loss, calculating mean cost values, training a regression model, optimizing a probability threshold, analyzing a plurality of inputs to generate a prediction, and transmitting the prediction. A computing system includes a transceiver; a processor; and a memory storing instructions that, when executed by the processor, cause the computing system to receive answers, transmit the answers, receive a prediction, when the prediction is repairable, generate a repair suggestion, and when the prediction is total loss, generate a settlement offer. A non-transitory computer readable medium containing program instructions that when executed, cause a computer to receive answers, transmit the answers, receive a prediction, when the prediction is repairable, generate a repair suggestion, and when prediction is total loss, generate a settlement offer.

公开(公告)号：US20240370937A1

公开(公告)日：2024-11-07

申请号：US18773136

申请日：2024-07-15

Applicant: State Farm Mutual Automobile Insurance Company

Inventor： Carlee A. Clymer ,  Gary Foreman ,  Ronald R. Duehr ,  Denson Smith ,  Vincent M. Hummel ,  Bradley J. Walder ,  Chad Mychal Hirst ,  Justin Devore ,  Shane Tomlinson ,  David A. Pluimer ,  Pavan Kumar Bhagavatula ,  John Westhues ,  Tracey Leigh Knorr ,  Erin E. Miller ,  Joshua T. Monk ,  Aaron Ames ,  John G. McConkey ,  Michael Cicilio Fresquez ,  Himanshu Chhita ,  Jason Beckman ,  Douglas A. Graff ,  Michele Wittman ,  Alexis Cates ,  Stephen Young ,  Rajesh Panicker ,  Yohan Santos ,  Stephen Wilson ,  Carrie A. Read ,  Michael Brown ,  Robin A. Rose

IPC: G06Q40/08 ,  G06N7/01 ,  G07C5/08

Abstract: A method of identifying a vehicle total loss claim includes retrieving a plurality of historical vehicle records, labeling the records as repaired or total loss, calculating mean cost values, training a regression model, optimizing a probability threshold, analyzing a plurality of inputs to generate a prediction, and transmitting the prediction. A computing system includes a transceiver; a processor; and a memory storing instructions that, when executed by the processor, cause the computing system to receive answers, transmit the answers, receive a prediction, when the prediction is repairable, generate a repair suggestion, and when the prediction is total loss, generate a settlement offer. A non-transitory computer readable medium containing program instructions that when executed, cause a computer to receive answers, transmit the answers, receive a prediction, when the prediction is repairable, generate a repair suggestion, and when prediction is total loss, generate a settlement offer.

公开(公告)号：US12045893B2

公开(公告)日：2024-07-23

申请号：US18091702

申请日：2022-12-30

Applicant: State Farm Mutual Automobile Insurance Company

Inventor： Carlee A. Clymer ,  Gary Foreman ,  Ronald R. Duehr ,  Denson Smith ,  Vincent M. Hummel ,  Bradley J Walder ,  Chad Mychal Hirst ,  Justin Devore ,  Shane Tomlinson ,  David A Pluimer ,  Pavan Kumar Bhagavatula ,  John Westhues ,  Tracey Leigh Knorr ,  Erin E. Miller ,  Joshua T. Monk ,  Aaron Ames ,  John G. McConkey ,  Michael Cicilio Fresquez ,  Himanshu Chhita ,  Jason Beckman ,  Douglas A. Graff ,  Michele Wittman ,  Alexis Cates ,  Stephen Young ,  Rajesh Panicker ,  Yohan Santos ,  Stephen Wilson ,  Carrie A Read ,  Michael Brown ,  Robin A Rose

IPC: G06Q40/00 ,  G06N7/01 ,  G06Q40/08 ,  G07C5/08

CPC classification number: G06Q40/08 ,  G06N7/01 ,  G07C5/0808 ,  G07C5/0841

Abstract: A method of identifying a vehicle total loss claim includes retrieving a plurality of historical vehicle records, labeling the records as repaired or total loss, calculating mean cost values, training a regression model, optimizing a probability threshold, analyzing a plurality of inputs to generate a prediction, and transmitting the prediction. A computing system includes a transceiver; a processor; and a memory storing instructions that, when executed by the processor, cause the computing system to receive answers, transmit the answers, receive a prediction, when the prediction is repairable, generate a repair suggestion, and when the prediction is total loss, generate a settlement offer. A non-transitory computer readable medium containing program instructions that when executed, cause a computer to receive answers, transmit the answers, receive a prediction, when the prediction is repairable, generate a repair suggestion, and when prediction is total loss, generate a settlement offer.

公开(公告)号：US20230222179A1

公开(公告)日：2023-07-13

申请号：US18110510

申请日：2023-02-16

Applicant: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

Inventor： He Yang ,  Bradley A. Sliz ,  Carlee A. Clymer ,  Jennifer Malia Andrus

IPC: G06Q40/08 ,  G06V10/82 ,  G06V10/74 ,  G06N3/08 ,  G06F16/583

CPC classification number: G06F18/22 ,  G06V10/82 ,  G06F18/214 ,  G06V10/761 ,  G06Q40/08 ,  G06N3/08 ,  G06F16/583 ,  G06V2201/08

Abstract: In a computer-implemented method and associated tangible non-transitory computer-readable medium, an image of a damaged vehicle may be analyzed to generate a repair estimate. A dataset populated with digital images of damaged vehicles and associated claim data may be used to train a deep learning neural network to learn damaged vehicle image characteristics that are predictive of claim data characteristics, and a predictive similarity model may be generated. Using the predictive similarity model, one or more similarity scores may be generated for a digital image of a newly damaged vehicle, indicating its similarity to one or more digital images of damaged vehicles with known damage level, repair time, and/or repair cost. A repair estimate may be generated for the newly damaged vehicle based on the claim data associated with images that are most similar to the image of the newly damaged vehicle.

公开(公告)号：US11574366B1

公开(公告)日：2023-02-07

申请号：US16593355

申请日：2019-10-04

Applicant: STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY

Inventor： Carlee A. Clymer ,  Gary Foreman ,  Ronald R. Duehr ,  Denson Smith ,  Vincent M. Hummel ,  Bradley J. Walder ,  Chad Mychal Hirst ,  Justin Devore ,  Shane Tomlinson ,  David A. Pluimer ,  Pavan Bhagavatula ,  John Westhues ,  Tracey Leigh Knorr ,  Erin E. Miller ,  Joshua T. Monk ,  Aaron Ames ,  John G. McConkey ,  Michael Cicilio Fresquez ,  Himanshu Chhita ,  Jason Beckman ,  Douglas A. Graff ,  Michele Wittman ,  Alexis Danielle Cates ,  Stephen Young ,  Rajesh Panicker ,  Yohan Santos ,  Stephen Wilson ,  Carrie A. Read ,  Michael Brown ,  Robin A. Rose

IPC: G06Q40/08 ,  G07C5/08 ,  G06N7/00

Abstract: A method of identifying a vehicle total loss claim includes retrieving a plurality of historical vehicle records, labeling the records as repaired or total loss, calculating mean cost values, training a regression model, optimizing a probability threshold, analyzing a plurality of inputs to generate a prediction, and transmitting the prediction. A computing system includes a transceiver; a processor; and a memory storing instructions that, when executed by the processor, cause the computing system to receive answers, transmit the answers, receive a prediction, when the prediction is repairable, generate a repair suggestion, and when the prediction is total loss, generate a settlement offer. A non-transitory computer readable medium containing program instructions that when executed, cause a computer to receive answers, transmit the answers, receive a prediction, when the prediction is repairable, generate a repair suggestion, and when prediction is total loss, generate a settlement offer.