Granted Patent B2

US 12,493,855 · App. 18/977,458 · Granted Dec 9, 2025

Inventors: Daniel James Thyer (Charlotte, NC); Matthew Doucette (Parker, TX); Peter Douglas Jackson (Alpharetta, GA); Robert Lee Martin, Jr. (Lucas, TX); Justin Michael Brown (Coppell, TX); Justin Corless (Flower Mound, TX); Swapna Muthuru (Frisco, TX); Carolina Lopez (Fort Worth, TX)

Assignee: Rehrig Pacific Company

G06Q10/0875

Abstract

Claims (98)

1 . A method for identifying a SKU of a package using a computer system having at least one processor, wherein the computer system stores a plurality of pick lists, wherein each pick list indicates a quantity of each of a plurality of desired SKUs to be placed on one of a plurality of pallets, wherein the plurality of desired SKUs are each associated with a package of beverage containers, the method including:

a) the computer system identifying an initial location of the package;

b) taking at least one image of a package on a conveyor;

c) receiving the at least one image in the computer system;

d) based upon the at least one image and based upon the initial location, the computer system determining a SKU associated with the package; and

e) comparing the SKU determined in step d) with at least one of the plurality of desired SKUs.

2 . The method of claim 1 wherein step e) includes comparing the SKU determined in step d) with the plurality of desired SKUs on the plurality of pick lists, the method further including:

f) based upon the comparison in step e), directing the package toward one of the plurality of pallets.

3 . The method of claim 1 , the method further including:

f) based upon the comparison in step e), directing the package toward one of the plurality of pallets;

g) instructing a pick of a first SKU of the plurality of desired SKUs of the plurality of pick lists, wherein the plurality of pick lists for the plurality of pallets are a first wave;

h) receiving an instruction to close the first wave without the computer system determining that a package is associated with the first SKU in step d); and

i) adjusting an invoice associated with one of the plurality of pallets based upon step h).

4 . The method of claim 1 , the method further including:

f) based upon the comparison in step e), directing the package toward one of the plurality of pallets;

g) instructing a pick of a first SKU of the plurality of desired SKUs of the plurality of pick lists, wherein the plurality of pick lists for the plurality of pallets are a first wave;

h) after step g), receiving an instruction from a user to skip the pick of the first SKU;

i) after step h), instructing a pick of a second SKU of the plurality of desired SKUs of the plurality of pick lists, wherein the first SKU is different from the second SKU; and

i), instructing the pick of the first SKU.

5 . The method of claim 1 wherein step a) is performed by an imaging system including at least one camera, the method further including:

f) based upon the comparison in step e), directing the package to an area proximate the conveyor upstream of the imaging system.

6 . The method of claim 1 wherein step d) includes the computer system inferring the SKU associated with the package using at least one machine learning model, wherein the computer system includes at least one non-transitory computer-readable media storing the at least one machine learning model, wherein the at least one machine learning model is trained with a plurality of images of packages of beverage containers.

7 . The method of claim 1 wherein the computer system includes at least one non-transitory computer-readable media storing at least one machine learning model, wherein the at least one machine learning model is trained with a plurality of images of packages of beverage containers and wherein the method includes:

f) the computer system inferring the SKU associated with the package using the at least one machine learning model;

g) the computer system analyzing the at least one image using text matching;

h) the computer system analyzing the at least one image using supervised contrastive learning and nearest neighbor methods; and

i) the computer system determining the SKU associated with the package in step d) based upon at least one of step f) or step g) or step h).

8 . The method of claim 7 wherein step g) includes using a decision forest.

9 . A computing system for identifying a SKU of a package of beverage containers comprising:

at least one processor; and

at least one non-transitory computer-readable media storing:

at least one machine learning model that has been trained with a plurality of images of packages of beverage containers; and

instructions that, when executed by the at least one processor, cause the computing system to perform the following operations:

a) receiving at least one image of a package on a conveyor, wherein the package is a package of beverage containers;

b) receiving an initial location of the package;

c) after operation b), identifying a SKU associated with the package based upon the initial location and based upon the at least one image using the at least one machine learning model; and

d) comparing the SKU identified in step c) to at least one desired SKU.

10 . The computing system of claim 9 wherein the computing system stores a plurality of pick lists, wherein each pick list indicates a quantity of each of a plurality of desired SKUs to be placed on one of a plurality of pallets, wherein operation d) includes comparing the SKU identified in step c) with at least one of the plurality of desired SKUs, wherein the operations further include:

e) based upon the comparison in operation d), directing the package toward one of the plurality of pallets.

11 . The computing system of claim 10 wherein the operations further include:

f) instructing a pick of a first desired SKU of the plurality of desired SKUs of the plurality of pick lists, wherein the plurality of pick lists for the plurality of pallets are a first wave;

g) receiving an instruction to close the first wave without the computing system having determined that a package is associated with the first desired SKU in operation d); and

h) adjusting an invoice associated with one of the plurality of pallets based upon operation g).

12 . The computing system of claim 10 wherein the operations further include:

f) instructing a pick of a first desired SKU of the plurality of desired SKUs of the plurality of pick lists, wherein the plurality of pick lists for the plurality of pallets are a first wave;

g) after operation f), receiving an instruction from a user to skip the pick of the first desired SKU;

h) after operation g), instructing a pick of a second desired SKU of the desired SKUs of the plurality of pick lists; and

i) after operation h), instructing the pick of the first SKU.

13 . A validation system including the computing system of claim 9 , the validation system further including an imaging system including at least one camera, the operations further including:

e) based upon the comparison in operation d), directing the package to an area proximate the conveyor upstream of the imaging system.

14 . The computing system of claim 10 wherein the initial location of the package in step b) is the initial location of the package prior to being placed on the conveyor.

15 . The computing system of claim 10 wherein the initial location of the package is determined based upon at least one initial image.

16 . The computing system of claim 9 wherein operation c) further includes inferring a plurality of classifications each at a confidence level, analyzing the at least one image to detect text, and augmenting the confidence level of at least one of the plurality of classifications based upon the detected text, wherein a size of the augmentation is based upon a number of classifications with which the detected text is associated.

17 . The computing system of claim 9 wherein the at least one image is a plurality of images and wherein operation c) includes:

e) determining at least one classification independently based upon each of the plurality of images; and

f) identifying the SKU associated with the package based upon the classifications determined in step e);

wherein operation e) includes inferring the at least one classification independently based upon each of the plurality of images using the at least one machine learning model.

18 . A computing system for identifying a SKU of a package of beverage containers comprising:

at least one processor; and

at least one non-transitory computer-readable media storing:

instructions that, when executed by the at least one processor, cause the computing system to perform the following operations:

a) receiving a plurality of overhead images of a package as it picked and placed on a conveyor;

b) determining a location of the package in at least one of the plurality of images;

c) identifying a SKU associated with the package based upon the location; and

d) comparing the SKU identified in step c) to at least one desired SKU on at least one picklist.

19 . The computing system of claim 18 further including:

e) directing the package toward one of a plurality of final conveyors based upon the comparison of step d).

20 . The computing system of claim 19 further including an overhead camera configured to generate the plurality of images.

21 . The computing system of claim 19 wherein the at least one non-transitory computer-readable media further stores at least one machine learning model trained with images of packages of beverage containers and wherein the operations further include:

f) receiving at least one package image of the package;

g) generating an output based upon the at least one package image using the at least one machine learning model; and

h) using the output to identify an associated SKU of a subsequent package.

22 . A method for identifying a SKU of a package using a computer system having at least one processor, the method including:

a) instructing a pick of a first desired SKU of a plurality of desired SKUs on a pick list, wherein the first desired SKU has an appearance unknown to the computer system;

b) receiving at least one image of a package in the computer system, wherein the package is a package of beverage containers;

c) the computer system generating an output based upon the at least one image using an image feature extractor;

d) the computer system comparing the output of step c) to a plurality of known outputs each having an associated known SKU using a feature similarity technique;

e) based upon step d), the computer system determining that a SKU of the package is different from the known SKUs associated with the plurality of known outputs;

f) the computer system instructing a user to scan a barcode on the package based upon step e);

g) based upon step e) and step f), the computer system determining that the SKU of the package is the first desired SKU; and

h) based upon step g) the computer system diverting the package.

23 . The method of claim 22 wherein in step d) the computer system performs a nearest neighbor technique and weighs each of a plurality of known outputs based upon a distance of each of the plurality of known outputs to the output of step c).

24 . The method of claim 22 wherein the package is a first package and the output is a first output, the method further including:

i) after step g), receiving at least one image of a second package in the computer system;

j) the computer system generating a second output based upon the at least one image of the second package using the image feature extractor;

k) the computer system comparing the second output of step j) to the plurality of known outputs and the first output using the feature similarity technique;

l) based upon step k), the computer system determining that a SKU of the second package is the first desired SKU; and

m) based upon step l), the computer system diverting the second package.

25 . A method for identifying a SKU of a package using a computer system having at least one processor, the method including:

a) instructing a pick of a first desired SKU of a plurality of desired SKUs on a pick list, wherein the first desired SKU has an expected appearance in the computer system;

b) receiving at least one image of a package in the computer system, wherein the package is a package of beverage containers;

c) the computer system generating an output based upon the at least one image using an image feature extractor;

d) the computer system comparing the output of step c) to a plurality of known outputs each having an associated known SKU using a feature similarity technique;

e) based upon step d), the computer system determining distances between the output and the plurality of known outputs;

f) based upon step a) and step e) the computer system determining that the SKU of the package is the first desired SKU, but that an appearance of the first desired SKU has changed; and

g) based upon step f), the computer system diverting the package.

26 . The method of claim 25 wherein in step f) the computer system performs a nearest neighbor technique and weighs each of a plurality of known outputs based upon the distance of each of the plurality of known outputs to the output of step c).

27 . The method of claim 25 wherein the computer system instructs a user to scan a barcode on the package based upon step e).

Assignments (1)

Continuity (6)

References Cited (377)