Granted Patent B2

US 12,236,677 · App. 17/248,794 · Granted Feb 25, 2025

Inventors: Sophie Bermudez (Washington, DC); Alexandra Colevas (Arlington, VA); Michael Saia (New York, NY); Kaylyn Gibilterra (New York, NY); Sarah J. Cunningham (Arlington, VA); Salik Shah (Washington, DC)

Assignee: Capital One Services, LLC

G06V20/10G06N20/00G06Q30/0278G06Q30/0601H04L47/781H04L47/788

Abstract

Claims (76)

1. A method comprising:

receiving, by a device, a plurality of images that depict a plurality of assets;

determining, by the device and based on a valuation model, valuation information that identifies estimated values associated with the plurality of assets,

wherein the valuation model is trained based on one or more parameters associated with the plurality of images and based on historical data associated with using images to evaluate assets;

determining, by the device, a selected allocation of the plurality of assets for a plurality of recipients using an allocation model and based on allocation information that identifies bids or priority levels of the plurality of recipients with regard to the plurality of assets,

wherein the allocation model receives, as input, at least one of:

the estimated values, or

the allocation information, and

wherein the allocation model outputs the selected allocation; and

performing, by the device, one or more actions based on the selected allocation.

2. The method of claim 1 , further comprising:

providing, to a plurality of user devices, at least a portion of the valuation information; and

wherein receiving the allocation information comprises:

receiving the allocation information from the plurality of user devices.

3. The method of claim 1 , wherein the allocation information includes, for each of the plurality of recipients, a rank value for each of the plurality of assets.

4. The method of claim 1 , wherein the allocation model comprises a machine learning model trained using historical data associated with prior asset allocations, prior estimated values, and prior allocation information.

5. The method of claim 1 , wherein the allocation model comprises an optimization model, the optimization model comprising one or more of:

a vector optimization model,

a multi-object optimization model, or

a Pareto optimization model.

6. The method of claim 1 , further comprising:

receiving updated allocation information after determining the selected allocation; and

determining, using the allocation model, an updated allocation of the plurality of assets based on the updated allocation information.

7. The method of claim 1 , wherein performing the one or more actions comprises:

generating, based on the selected allocation, a document that indicates, for each of the plurality of assets, a corresponding recipient of the plurality of recipients.

8. A device, comprising:

one or more memories; and

one or more processors, coupled to the one or more memories, configured to:

receive a plurality of images that depict a plurality of assets;

determine, based on a valuation model, valuation information that identifies estimated values associated with the plurality of assets,

wherein the valuation model is trained based on one or more parameters associated with the plurality of images and based on historical data associated with using images to evaluate assets;

determine a selected allocation of the plurality of assets for a plurality of recipients using an allocation model and based on allocation information that identifies bids or priority levels of the plurality of recipients with regard to the plurality of assets,

wherein the allocation model receives, as input, at least one of:

the estimated values, or

the allocation information, and

wherein the allocation model outputs the selected allocation; and

perform one or more actions based on the selected allocation.

9. The device of claim 8 , wherein the one or more processors are further configured to:

provide, to a plurality of user devices, at least a portion of the valuation information; and

wherein the one or more processors, when receiving the allocation information, are configured to:

receive the allocation information from the plurality of user devices.

10. The device of claim 8 , wherein the allocation information includes, for each of the plurality of recipients, a rank value for each of the plurality of assets.

11. The device of claim 8 , wherein the allocation model comprises a machine learning model trained using historical data associated with prior asset allocations, prior estimated values, and prior allocation information.

12. The device of claim 8 , wherein the allocation model comprises an optimization model, the optimization model comprising one or more of:

a vector optimization model,

a multi-object optimization model, or

a Pareto optimization model.

13. The device of claim 8 , wherein the one or more processors are further configured to:

receive updated allocation information after determining the selected allocation; and

determine, using the allocation model, an updated allocation of the plurality of assets based on the updated allocation information.

14. The device of claim 8 , wherein the one or more processors, when performing the one or more actions, are configured to:

generate, based on the selected allocation, a document that indicates, for each of the plurality of assets, a corresponding recipient of the plurality of recipients.

15. A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:

one or more instructions that, when executed by one or more processors of a device, cause the device to:

receive a plurality of images that depict a plurality of assets;

determine, based on a valuation model, valuation information that identifies estimated values associated with the plurality of assets,

wherein the valuation model is trained based on one or more parameters associated with the plurality of images and based on historical data associated with using images to evaluate assets;

determine a selected allocation of the plurality of assets for a plurality of recipients using an allocation model and based on allocation information that identifies bids or priority levels of the plurality of recipients with regard to the plurality of assets,

wherein the allocation model receives, as input, at least one of:

the estimated values, or

the allocation information, and

wherein the allocation model outputs the selected allocation; and

perform one or more actions based on the selected allocation.

16. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions further cause the device to:

provide, to a plurality of user devices, at least a portion of the valuation information; and

wherein the one or more instructions, that cause the device to receive the allocation information, cause the device to:

receive the allocation information from the plurality of user devices.

17. The non-transitory computer-readable medium of claim 15 , wherein the allocation information includes, for each of the plurality of recipients, a rank value for each of the plurality of assets.

18. The non-transitory computer-readable medium of claim 15 , wherein the allocation model comprises a machine learning model trained using historical data associated with prior asset allocations, prior estimated values, and prior allocation information.

19. The non-transitory computer-readable medium of claim 15 , wherein the allocation model comprises an optimization model, the optimization model comprising one or more of:

a vector optimization model,

a multi-object optimization model, or

a Pareto optimization model.

20. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions further cause the device to:

receive updated allocation information after determining the selected allocation; and

determine, using the allocation model, an updated allocation of the plurality of assets based on the updated allocation information.

Assignments (1)

Continuity (3)

References Cited (26)