Intelligence platform for automated retrieval or protection of a package or a person by an unmanned vehicle (UV)

• US 10,402,774 B1
• Filed: 07/25/2018
• Issued: 09/03/2019
• Est. Priority Date: 07/25/2018
• Status: Active Grant

• Current Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Original Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Inventors: Phillips, Jeremy, Park, Kevin, Blackman, Shane
• Primary Examiner(s): Elchanti, Hussein
• Application Number:
  US16/045,172
• Time in Patent Office: 405 Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 10/0833 Tracking

Abstract

An intelligence platform determines that a package was delivered to a location, and receives real-time information associated with the package or location. The real-time information includes sensor data received from one or more sensor devices disposed proximate to the package, or third party data received from one or more third party devices associated with a geographic region that includes the location to which the package was delivered. The intelligence platform determines, using a machine learning model, a score for the package based on the real-time information, where the score predicts a measure of vulnerability of the package, and determines whether to retrieve or protect the package based on the score. The intelligence platform selects an unmanned vehicle (UV) to retrieve or protect the package based on vehicular data, and transmits instructions to the UV to cause the UV to navigate to the package and retrieve or protect the package.

Claims

1. A method, comprising:

determining, by a computing resource of a cloud computing environment, that a package was delivered to a location;

receiving, by a computing resource of the cloud computing environment, real-time information associated with the package or the location to which the package was delivered,

wherein the real-time information includes;

sensor data received from one or more sensor devices disposed proximate to the package, and

third party data received from one or more third party devices associated with a geographic region that includes the location to which the package was delivered;

determining, by a computing resource of the cloud computing environment and using a first machine learning model, a first score for the package based on the real-time information,

wherein the first score predicts a measure of vulnerability of the package;

determining, by a computing resource of the cloud computing environment, whether to retrieve or protect the package based on the first score for the package;

receiving, by a computing resource of the cloud computing environment, vehicular data associated with a plurality of unmanned aerial vehicles (UAVs) capable of retrieving or protecting the package;

determining, by a computing resource of the cloud computing environment and using a second machine learning model, a second score for one or more of the plurality of UAVs,

wherein the second score predicts a measure of confidence that a first UAV, of the one or more of the plurality of UAVs, is capable of retrieving or protecting the package;

selecting, by a computing resource of the cloud computing environment, the first UAV, of the one or more of the plurality of UAVs, to retrieve or protect the package based on the second score;

determining, by a computing resource of the cloud computing environment, instructions for causing the first UAV to navigate to the package and retrieve or protect the package; and

transmitting, by a computing resource of the cloud computing environment, the instructions to the first UAV to cause the first UAV to navigate to the package and retrieve or protect the package.

2. The method of claim 1, wherein the sensor data includes:

data associated with an external temperature or humidity outside of the package,

data associated with an internal temperature or humidity inside of the package,

data associated with a spatial position of the package,

data associated with a building disposed proximate to the package,

data associated with a person disposed proximate to the package, or

data associated with an animal partially contained by the package.

3. The method of claim 1, wherein the third party data includes:

emergency data associated with the geographic region,

weather data associated with the geographic region, or

crime data associated with the geographic region.

4. The method of claim 1, wherein the vehicular data includes:

data indicating a geographic location associated with a UAV included in the plurality of UAVs,

data indicating a travel range associated with the UAV included in the plurality of UAVs, or

data indicating traffic conditions associated with the UAV included in the plurality of UAVs.

5. The method of claim 1, further comprising:

causing the first UAV to redeliver the package to a sender of the package or an alternative location.

6. The method of claim 1, wherein the instructions are configured to cause the first UAV to record audio data associated with the package, record video data associated with the package, capture image data associated with the package, or contact one or more first responders based on the instructions.

7. The method of claim 1, wherein the instructions are configured to cause the first UAV to deploy an item to protect or retrieve the package based on the instructions, and

wherein the item includes:

a net,

a rope,

a hook,

a magnet,

an umbrella,

a mask,

a tool,

an inflatable device,

a lighting device,

food,

water, or

medicine.

8. The method of claim 1, further comprising:

determining that the first UAV is no longer capable of retrieving or protecting the package; and

transmitting instructions to a second UAV to cause the second UAV to navigate to the package and retrieve or protect the package based on determining that the first UAV is no longer capable of retrieving or protecting the package.

9. The method of claim 8, wherein the instructions to the second UAV are transmitted by a computing resource of the cloud computing environment or the first UAV.

10. A device, comprising:

one or more memories; and

one or more processors, communicatively coupled to the one or more memories, to;

determine that a package was delivered to a location;

receive real-time information associated with the package or the location to which the package was delivered,

wherein the real-time information includes;

sensor data received from one or more sensor devices disposed proximate to the package, or

third party data received from one or more third party devices associated with a geographic region that includes the location to which the package was delivered;

determine, using a machine learning model, a score for the package based on the real-time information,

wherein the score predicts a measure of vulnerability of the package;

determine whether to retrieve or protect the package based on the score for the package;

receive vehicular data associated with a plurality of unmanned aerial vehicles (UAVs) capable of retrieving or protecting the package;

select a particular UAV, of the one or more of the plurality of UAVs, to retrieve or protect the package based on the vehicular data;

determine instructions for causing the particular UAV to navigate to the package and retrieve or protect the package; and

transmit the instructions to the particular UAV to cause the particular UAV to navigate to the package and retrieve or protect the package.

11. The device of claim 10, wherein the package includes a credit card, a debit card, cash, a check, or a cashier'"'"'s check.

12. The device of claim 10, wherein the package includes an animal or food, and

wherein the sensor data is associated with a health or safety of the animal or the food.

13. The device of claim 10, wherein at least one wall of the package comprises a magnet, and

wherein the instructions are configured to cause the particular UAV to deploy a magnetic member to retrieve the package using the magnet.

14. The device of claim 10, wherein the sensor data includes:

data associated with an external temperature or humidity outside of the package,

data associated with an internal temperature or humidity inside of the package,

data associated with a spatial position of the package,

data associated with a building disposed proximate to the package,

data associated with a person disposed proximate to the package, or

data associated with an animal partially contained by the package.

15. The device of claim 10, wherein the sensor data includes biometric information, pulmonary information, or respiratory information associated with a person located proximate to the package.

16. The device of claim 10, wherein the third party data includes:

emergency data associated with the geographic region,

weather data associated with the geographic region, or

crime data associated with the geographic region.

17. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors, cause the one or more processors to;

determine that a package was delivered to a location;

receive real-time information associated with the location or the package,

wherein the real-time information includes;

sensor data received from one or more sensor devices disposed proximate to the package, or

third party data received from one or more third party devices associated with a geographic region that includes the location;

determine, using a machine learning model, a score for the package based on the real-time information,

wherein the score predicts a measure of vulnerability of the package;

determine whether to retrieve or protect the package based on the score;

receive vehicular data associated with a plurality of unmanned aerial vehicles (UAVs) capable of retrieving or protecting the package;

select a particular UAV, of the plurality of UAVs, to retrieve or protect the package based on the vehicular data;

determine instructions for causing the particular UAV to navigate to the package and retrieve or protect the package; and

transmit the instructions to the particular UAV to cause the particular UAV to navigate to the package and retrieve or protect the package.

18. The non-transitory computer-readable medium of claim 17, wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

receive real-time spatial location data associated with the package;

determine that the package is moving; and

transmit the instructions to the particular UAV to retrieve or protect the package based on the real-time spatial location data,

wherein the instructions are configured to cause the particular UAV to record video data associated with movement of the package.

19. The non-transitory computer-readable medium of claim 17, wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

receive real-time safety data associated with a food contained by the package; and

transmit the instructions to the particular UAV to retrieve or protect the package based on the real-time safety data.

20. The non-transitory computer-readable medium of claim 17, wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

determine that the particular UAV is no longer capable of retrieving or protecting the package; and

transmit instructions to another UAV, of the plurality of UAVs, to cause the other UAV to navigate to the package and retrieve or protect the package based on determining that the UAV is no longer capable of retrieving or protecting the package.