Predictive parcel damage identification, analysis, and mitigation

• US 10,796,423 B2
• Filed: 10/01/2018
• Issued: 10/06/2020
• Est. Priority Date: 09/29/2017
• Status: Active Grant

• Current Assignee: United Parcel Service Of America Incorporated (United Parcel Service Incorporated)
• Original Assignee: United Parcel Service Of America Incorporated (United Parcel Service Incorporated)
• Inventors: Goja, Asheesh
• Primary Examiner(s): Chu, Randolph I
• Application Number:
  US16/148,104
• Publication Number:
  US 20190102874A1
• Time in Patent Office: 736 Days
• Field of Search: None
• CPC Class Codes: B64C 39/024 of the remote controlled vehicle type, i.e. RPV
• CPC Class Codes: B64U 10/13 Flying platforms
• CPC Class Codes: B64U 2101/30 for imaging, photography or videography
• CPC Class Codes: B64U 2101/60 for transporting passengers; for transporting goods other than weapons
• CPC Class Codes: B64U 2201/10 autonomous, i.e. by navigating independently from ground or air stations, e.g. by using inertial navigation systems [INS]
• CPC Class Codes: B64U 30/26 Ducted or shrouded rotors
• CPC Class Codes: B64U 80/86 Land vehicles
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06F 18/2431 Multiple classes
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/06395 Quality analysis or management
• CPC Class Codes: G06T 2207/20076 Probabilistic image processing
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/20084 Artificial neural networks [ANN]
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/74 involving reference images or patches

Abstract

A first parcel digital image associated with a first interaction point is received. The first parcel digital image may be associated with a first parcel being transported to or from the first interaction point. At least a second parcel digital image associated with at least a second interaction point is further be received. The second parcel digital image may be associated with the first parcel being transported to or from the second interaction point. A first parcel damage analysis is automatically generated based at least in part on analyzing the first parcel digital image and the at least second parcel image. The damage analysis can include determining whether the first parcel is damaged above or below a threshold.

Claims

1. An apparatus for predictive parcel damage mitigation in a parcel transit network, the parcel transit network comprising an origin interaction point, a plurality of parcel interaction points, and a destination interaction point, the apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to:

receive a first plurality of parcel digital images from the origin interaction point, the first plurality of parcel digital images associated with a parcel being transported from the origin interaction point to the destination interaction point via the plurality of parcel interaction points;

receive a second plurality of parcel digital images of the parcel from a first parcel interaction point of the plurality of parcel interaction points, the first plurality of parcel digital images and the second plurality of parcel digital images representing a plurality of fields of view of the parcel; and

programmatically generate a first parcel damage analysis based upon the first plurality of parcel digital images, the second plurality of parcel digital images, and a machine learning model.

2. The apparatus of claim 1, wherein the program code further causes the apparatus to:

upon determining that a severity of the first parcel damage analysis is below a threshold,

transmit a first transit network interaction point condition confirmation based upon the first parcel damage analysis; and

upon determining that the severity of the first parcel damage analysis is above the threshold, programmatically generate a first transit network interaction point damage analysis based upon the first parcel damage analysis and the machine learning model.

3. The apparatus of claim 1, wherein the program code further causes the apparatus to transmit a first transit network interaction point damage mitigation instruction based upon a first transit network interaction point damage analysis.

4. The apparatus of claim 1, wherein the first parcel damage analysis comprises determining a first plurality of pose ranges for the first plurality of parcel digital images.

5. The apparatus of claim 4, wherein the first parcel damage analysis further comprises determining a second plurality of pose ranges for the second plurality of parcel digital images.

6. The apparatus of claim 5, wherein the first parcel damage analysis further comprises

determining a first plurality of parcel view overlaps based upon the first plurality of pose ranges;

and

determining a second plurality of parcel view overlaps based upon the second plurality of pose ranges.

7. The apparatus of claim 1, wherein the first parcel damage analysis comprises programmatically generating the first parcel damage analysis based upon a first plurality of parcel view overlaps, a second plurality of parcel view overlaps, and the machine learning model.

11. The method of claim 1, further comprising:

upon determining that severity of the first parcel damage analysis is above a threshold, generate a first transit network interaction point damage analysis based upon the first parcel damage analysis and the machine learning model; and

in response to the determining that the severity of the first parcel damage analysis being above the threshold, providing a transit network interaction point damage mitigation instruction, the transit network interaction point damage mitigation instruction includes providing an instruction to a device within a carrier route that includes the first interaction point and the second interaction point, the mitigation instruction includes a control signal to modify a condition to mitigate the damage.

12. The method of claim 1, wherein the first parcel damage analysis comprises determining a first pose range for the first parcel digital image, the first pose range corresponds to a restriction to what is visible to be captured by a digital image capturing device.

13. The method of claim 12, wherein the first parcel damage analysis further comprises determining a second pose range for the second digital image.

8. A computer-implemented method comprising:

receiving a first parcel digital image associated with a first interaction point, the first parcel digital image associated with a first parcel being transported to or from the first interaction point;

receiving at least a second parcel digital image associated with at least a second interaction point, the second parcel digital image associated with the first parcel being transported to or from the second interaction point; and

automatically generate a first parcel damage analysis based at least in part on analyzing the first parcel digital image and the at least second parcel image, the damage analysis includes determining whether the first parcel is damaged above or below a threshold.

9. The method of claim 8, wherein the first parcel damage analysis includes a parcel damage analysis summary that comprises one or more of:

a parcel type, a parcel damage type, a parcel damage location identifier, a parcel damage severity, a parcel damage mitigation recommendation, and a parcel damage restoration estimate.

10. The method of claim 8, further comprising:

receive a third plurality parcel digital images of the first parcel from a third parcel interaction point, the third plurality of parcel digital images representing a plurality of fields of view of the parcel taken by an image capturing device along a carrier route, the first interaction point, the second interaction point, and the third interaction point each being different locations along the carrier route;

generate a second parcel damage analysis based upon the first parcel digital image, the second parcel digital image, the third plurality of parcel digital images, and a neural network machine learning model; and

upon determining that a second severity of the second parcel damage analysis is below a second threshold, transmit a transit network interaction point condition confirmation, the transit network interaction point condition confirmation corresponds to an authorization for the first parcel to continue traversing along the carrier route.

14. The method of claim 8, wherein the first parcel damage analysis comprises determining parcel view overlap duplication associated with the first parcel between the first parcel digital image and the second parcel digital image.