View source for 20230136983. METHODS AND SYSTEMS FOR USING TRAINED GENERATIVE ADVERSARIAL NETWORKS TO IMPUTE 3D DATA FOR UNDERWRITING, CLAIM HANDLING AND RETAIL OPERATIONS simplified abstract (STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY)

=METHODS AND SYSTEMS FOR USING TRAINED GENERATIVE ADVERSARIAL NETWORKS TO IMPUTE 3D DATA FOR UNDERWRITING, CLAIM HANDLING AND RETAIL OPERATIONS=


==Organization Name==

[[:Category:STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY|STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY]]


[[Category:STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY]]

==Inventor(s)==

[[:Category:Ryan Knuffman of Danvers IL (US)|Ryan Knuffman of Danvers IL (US)]][[Category:Ryan Knuffman of Danvers IL (US)]]

==METHODS AND SYSTEMS FOR USING TRAINED GENERATIVE ADVERSARIAL NETWORKS TO IMPUTE 3D DATA FOR UNDERWRITING, CLAIM HANDLING AND RETAIL OPERATIONS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20230136983 titled 'METHODS AND SYSTEMS FOR USING TRAINED GENERATIVE ADVERSARIAL NETWORKS TO IMPUTE 3D DATA FOR UNDERWRITING, CLAIM HANDLING AND RETAIL OPERATIONS

==Simplified Explanation==

The abstract describes a method, computing system, and computer-readable medium for using a trained generative adversarial network (GAN) to improve various operations such as underwriting, claim handling, retail operations, vehicle orientation, and navigation. 

* The method involves receiving a 3D point cloud and using a trained GAN to generate a gap-filled semantically-segmented 3D point cloud.
* The computing system includes processors and memories with computer-executable instructions to receive a 3D point cloud and generate a gap-filled semantically-segmented 3D point cloud using the trained GAN.
* The computer-readable medium stores computer-executable instructions to receive a 3D point cloud and generate a gap-filled semantically-segmented 3D point cloud using a trained GAN.

Potential Applications:
* Underwriting improvement: The technology can be used to analyze 3D point clouds of properties or assets to assess risks and make more accurate underwriting decisions.
* Claim handling enhancement: By analyzing 3D point clouds of damaged properties or assets, the technology can help insurance companies process claims more efficiently and accurately.
* Retail operations optimization: The technology can be utilized to analyze 3D point clouds of retail spaces, improving store layout, product placement, and customer experience.
* Vehicle orientation and navigation improvement: By analyzing 3D point clouds of the surroundings, the technology can assist in vehicle orientation and navigation, enhancing safety and efficiency.

Problems Solved:
* Incomplete 3D point clouds: The technology fills gaps in 3D point clouds, providing a more complete and accurate representation of the object or environment.
* Semantic segmentation: The technology categorizes different parts or objects within the 3D point cloud, enabling better understanding and analysis of the data.

Benefits:
* Enhanced decision-making: The technology improves the accuracy and reliability of underwriting decisions, claim handling, and retail operations planning.
* Efficiency and automation: By automating the analysis of 3D point clouds, the technology reduces manual effort and speeds up processes.
* Improved safety and navigation: The technology assists in vehicle orientation and navigation, contributing to safer and more efficient transportation.


==Original Abstract Submitted==

a method for using a trained generative adversarial network to improve underwriting, claim handling and retail operations includes receiving a 3d point cloud; and generating a gap-filled semantically-segmented 3d point cloud using a trained generative adversarial network. a computing system for using a trained generative adversarial network to improve vehicle orientation and navigation includes one or more processors, and one or more memories having stored thereon computer-executable instructions that, when executed, cause the computing system to: receive a 3d point cloud; and generate a gap-filled semantically-segmented 3d point cloud using the trained generative adversarial network. a non-transitory computer-readable medium having stored thereon computer-executable instructions that, when executed, cause a computer to: receive a 3d point cloud; and generate a gap-filled semantically-segmented 3d point cloud using a trained generative adversarial network.



[[Category:G06T5/00]]
[[Category:G06T7/579]]
[[Category:G06N3/088]]
[[Category:G06N3/045]]