System and methodology to prevent false claims to delivered or rented goods

Patent metadata

Field	Value
Publication number	US-9953412-B1
Application number	US-201615331123-A
Country	US
Kind code	B1
Filing date	Oct 21, 2016
Priority date	Oct 21, 2016
Publication date	Apr 24, 2018
Grant date	Apr 24, 2018

Abstract

A method and system of assessing damage to an object. A first digital image of an object is taken at a first point in time with a first camera. A second digital image of the object is taken at a second point in time with a second camera, where the second point in time is after the first point in time. The first digital image and the second digital image may are compared to determine if there is damage to the object. In response to a determination that there is damage to the object, a potential source of the damage to the object is determined by analyzing historical trends of damage to historically damaged objects.

First claim

What is claimed is:

1. A method of assessing damage to an object, comprising the steps of:
taking a first digital image of the object at a first location and a first point in time with at least one first camera;
taking a second digital image of the object at a second location and a second point in time with at least one second camera, wherein the second point in time is after the first point in time;
comparing, by one or more processors, the first digital image and the second digital image and determining if there is damage to the object based on the comparison; and
in response to a determination that there is damage to the object, then determining, by the one or more processors, at least one potential source of the damage to the object by analyzing historical trends of damage to historically damaged objects, wherein the determining at least one potential source of the damage to the object comprises:
collecting information related to circumstances and locations of the object between the first point in time and the second point in time and between the first and second locations;
comparing the information related to the circumstances and locations of the object to information related to stored circumstances and stored locations of the historically damaged objects, the historical trends being computed based on patterns attributed to similarities in information related to the stored circumstances and stored locations of the historically damaged objects; and
determining the at least one potential source of the damage to the object based on similarities between the information related to circumstances and locations of the object and the information related to the stored circumstances and stored locations of the historically damaged objects,
wherein the information related to stored circumstances and stored locations of the historically damaged objects includes a database of a plurality of different stored circumstances and a plurality of different stored locations, and wherein said plurality of different stored circumstances and different stored locations include specific circumstances and locations along a plurality of different paths between the first and second locations.

2. The method of claim 1 , wherein the determining the at least one potential source of the damage to the object is performed by a service analytics engine to generate a trend report based on the circumstances of the object and the circumstances of the historically damaged objects.

3. The method of claim 2 , wherein the service analytics engine generates the trend report using a special purpose algorithms implemented by at least one of hardware or software to determine the at least one potential source of damage from the circumstances of the object and the circumstances of the historically damaged objects, wherein the at least one hard ware or software includes specialized, non-generic hardware and circuitry for executing only methods of determining the at least one potential source of damage.

4. The method of claim 3 , wherein the special purpose algorithm determines the at least one potential source of damage based on at least one result of one or more comparisons selected from the group consisting of:
a comparison of attributes of a scratch on the object and the historically damaged objects;
a comparison of attributes of a tear on the object and the historically damaged objects;
a comparison of attributes of a crack on the object and the historically damaged objects;
a comparison of attributes of an indentation on the object and the historically damaged objects;
a comparison of attributes of a missing component on the object and the historically damaged objects;
a comparison of attributes of a discoloration on the object and the historically damaged objects;
a comparison of attributes of a travel path of the object and the historically damaged objects;
a comparison of a brand of the object and the historically damaged objects;
a comparison of a model of the object and the historically damaged objects;
a comparison of attributes of personnel handling the object and the historically damaged objects;
a comparison of weight attributes of the object and the historically damaged objects;
a comparison of circumstantial weather attributes of the object and the historically damaged objects;
a comparison of utility attributes of the object and the historically damaged objects;
a comparison of seasonal attributes of the object and the historically damaged objects; and
combinations thereof.

5. The method of claim 1 , wherein the determination that there is damage to the object is based on at least one predetermined damage threshold.

6. The method of claim 5 , wherein the at least one predetermined damage threshold are associated with predefined normal wear and tear standards.

7. The method of claim 1 , wherein the determining at least one potential source of the damage to the object comprises comparing at least one of the first digital image of the object or the second digital image of the object to digital images of the historically damaged objects.

8. The method of claim 1 , comprising calculating a cost of damage to the object.

9. The method of claim 1 , wherein the method is implemented by at least one transportation carrier, and the step of comparison includes a comparison of attributes of personnel handling the object and the historically damaged objects.

10. The method of claim 9 , wherein the transportation carrier is selected from a group consisting of:
an airplane operator;
a train operator;
a boat operator;
a bus operator;
a motor coach operator;
a bicycle operator;
an automobile operator;
a trucking operator;
a shipping company;
a package handler; and
combinations thereof.

11. The method of claim 9 , wherein the at least one potential source of the damage to the object is selected from a group consisting of:
a route of the object;
equipment handling the object;
personnel handling the object;
a contractor of the transportation carrier; and
combinations thereof.

12. The method of claim 9 , wherein at least one of:
the first point in time is during a check-in procedure of the transportation carrier; or
the second point in time is during a final delivery procedure of the transportation carrier.

13. The method of claim 12 , wherein the first digital image is provided to a customer during the check-in procedure of the transportation carrier.

14. The method of claim 1 , wherein the comparing the first digital image and the second digital image is performed by a convolutional neural network algorithm.

15. The method of claim 1 , wherein the object is a rented or leased item.

16. The method of claim 7 , wherein the rented or leased item is selected from a group consisting of:
a vehicle;
an automobile;
a boat;
equipment;
furniture;
an appliance;
a tool;
clothing; and
combinations thereof.

17. The method of claim 1 , wherein at least one of the first digital image and the second digital image is at least one of:
a digital image;
a three dimensional image;
a x-ray image; and
combinations thereof.

18. A system that assesses damage to an object, comprising:
at least one first camera configured to take a first digital image of the object at a first point in time;
at least one second camera configured to take a second digital image of the object at a second point in time, wherein the second point in time is after the first point in time;
a comparison unit configured to compare, by one or more processors, the first d

Assignees

• IBM

Inventors

• Anderson Evelyn R
• Bender Michael
• Childress Rhonda L

Classifications

• G06V10/82

  using neural networks · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06F18/24

  Classification techniques · CPC title

• G06V10/454

  Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN] · CPC title

• G06T2207/10116

  X-ray image · CPC title