Structural characteristic extraction and insurance quote generation using 3D images

• US 10,521,865 B1
• Filed: 08/24/2016
• Issued: 12/31/2019
• Est. Priority Date: 12/11/2015
• Status: Active Grant

• Current Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Original Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Inventors: Spader, Timothy J., Dulee, Jr., George T., Yuhas, Donald, Brucker, Aaron, Stroh, Chris, Mousty, Jeffrey
• Primary Examiner(s): Shaikh, Mohammad Z
• Application Number:
  US15/245,659
• Time in Patent Office: 1,224 Days
• CPC Class Codes: G01C 11/025 by scanning the object
• CPC Class Codes: G01C 11/06 by comparison of two or more pictures of the same area
• CPC Class Codes: G06F 18/2413 based on distances to training or reference patterns
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G06T 1/0007 Image acquisition
• CPC Class Codes: G06T 2207/10012 Stereo images
• CPC Class Codes: G06T 2207/10021 Stereoscopic video; Stereoscopic image sequence
• CPC Class Codes: G06T 7/593 from stereo images
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/82 using neural networks
• CPC Class Codes: G06V 20/13 Satellite images
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: H04N 13/204 using stereoscopic image cameras stereoscopic photography G03B35/00

Abstract

An insurance server for generating a quote associated with an object pictured in a three-dimensional (3D) image may be provided. The insurance server may include a processor in communication with a memory. The insurance server may be configured to receive the 3D image including the object from a structural analysis computing device, and analyze the received 3D image. The insurance server may also be configured to determine a value of the object based upon the analysis, and generate a quote associated with the object based upon the determined value of the object. The insurance server may be further configured to transmit the quote for display at the structural analysis computing device for the customer'"'"'s review and/or approval.

Claims

1. An insurance server for generating a quote associated with an object pictured in a three-dimensional (3D) image, the insurance server comprising at least one processor in communication with a memory, wherein the at least one processor is programmed to:

retrieve, from a database, training data including a first plurality of three-dimensional (3D) training images, each of the first plurality of 3D training images including an insurable asset having a corresponding insurable asset value;

generate a machine learning model based on the first plurality of 3D training images;

receive the 3D image from a structural analysis computing device, wherein the 3D image is generated by an object sensor of the structural analysis computing device;

analyze, by the at least one processor, the received 3D image using a machine learning algorithm operating based on the generated machine learning model to automatically identify a plurality of insurable asset objects pictured in the 3D image;

determine a 3D training image associated with each of the insurable asset objects from the first plurality of 3D training images;

determine a value of each of the insurable asset objects based on the associated 3D training image and the training data;

generate an insurance quote based on the plurality of insurable asset objects, the 3D training image associated with each of the plurality of insurable asset objects, and the value of each of the insurable asset objects; and

transmit the insurance quote for display at the structural analysis computing device to facilitate providing insurance coverage based upon 3D image data.

2. The insurance server of claim 1, wherein the at least one processor is further programmed to analyze the received 3D image by automatically determining a first plurality of measurements associated with at least one of the plurality of insurable asset objects.

3. The insurance server of claim 2, wherein the first plurality of measurements includes at least one of wall lengths, wall heights, missing wall lengths, and missing wall heights.

4. The insurance server of claim 1, wherein the at least one processor is further programmed to analyze the received 3D image by extracting at least one material associated with at least one of the plurality of insurable asset objects.

5. The insurance server of claim 1, wherein the memory includes a cloud storage device.

6. The insurance server of claim 1, wherein the at least one processor is further programmed to facilitate display of a quote request app on the structural analysis computing device, wherein the quote request app is further programmed to display the plurality of insurable asset objects, the 3D training image associated with each of the plurality of insurable asset objects, and the value of each of the insurable asset objects.

7. The insurance server of claim 6, wherein the at least one processor is further programmed to receive user input from a user of the structural analysis computing device using the quote request app.

8. The insurance server of claim 7, wherein the user input includes an estimated value of at least one of the plurality of insurable asset objects.

9. The insurance server of claim 1, wherein the at least one processor is further programmed to store the plurality of insurable asset objects, and the value of each of the insurable asset objects as a baseline.

10. The insurance server of claim 9, wherein the at least one processor is further programmed to determine a pre-insured status of the plurality of insurable asset objects.

11. The insurance server of claim 1, wherein the at least one processor is further programmed to create an inventory of contents associated with the 3D image, the inventory including the identified plurality of insurable asset objects pictured in the 3D image.

12. A computer-implemented method for generating a quote associated with an object pictured in a three-dimensional (3D) image, the method implemented using an insurance server including a processor in communication with a memory, the method comprising:

retrieving, from a database, training data including a first plurality of three-dimensional (3D) training images each of the first plurality of 3D training images including an insurable asset having a corresponding insurable asset value;

generating a machine learning model based on the first plurality of 3D training images;

receiving the 3D image from a structural analysis computing device, wherein the 3D image is generated by an object sensor of the structural analysis computing device;

analyzing, by the processor, the received 3D image using a machine learning algorithm operating based on the generated machine learning model to automatically identify a plurality of insurable asset objects pictured in the 3D image;

determining a 3D training image associated with each of the insurable asset objects from the first plurality of 3D training images;

determining a value of each of the insurable asset objects based on the associated 3D training image and the training data;

generating an insurance quote based on the plurality of insurable asset objects, the 3D training image associated with each of the plurality of insurable asset objects, and the value of each of the insurable asset objects; and

transmitting the insurance quote for display at the structural analysis computing device to facilitate providing insurance based upon 3D image data.

13. The computer-implemented method of claim 12, wherein analyzing the received 3D image comprises automatically determining a first plurality of measurements associated with at least one of the plurality of insurable asset objects.

14. The computer-implemented method of claim 13, wherein the first plurality of measurements includes at least one of wall lengths, wall heights, missing wall lengths, and missing wall heights.

15. The computer-implemented method of claim 12, wherein analyzing the received 3D image comprises extracting at least one material associated with at least one of the plurality of insurable asset objects.

16. The computer-implemented method of claim 12 further comprising facilitating display of a quote request app on the structural analysis computing device, wherein the quote request app is further programmed to display the plurality of insurable asset objects, the 3D training image associated with each of the plurality of insurable asset objects, and the value of each of the insurable asset objects.

17. The computer-implemented method of claim 16 further comprising receiving user input from a user of the structural analysis computing device using the quote request app.

18. The computer-implemented method of claim 17, wherein the user input includes an estimated value of at least one of the plurality of insurable asset objects.

19. The computer-implemented method of claim 12 further comprising storing the plurality of insurable asset objects and the value of each of the insurable asset objects as a baseline.

20. The computer-implemented method of claim 19 further comprising determining a pre-insured status of the plurality of insurable asset objects.