Search

CA-3129719-C - DELIVERY SYSTEM

CA3129719CCA 3129719 CCA3129719 CCA 3129719CCA-3129719-C

Abstract

A delivery system generates a pick sheet containing a plurality of SKUs based upon an order. A loaded pallet is imaged to identify the SKUs on the loaded pallet, which are compared to the order prior to the loaded pallet leaving the distribution center. The loaded pallet may be imaged while being wrapped with stretch wrap. At the point of delivery, the loaded pallet may be imaged again and analyzed to compare with the pick sheet.

Inventors

  • Robert Lee, Jr. MARTIN
  • Deanna Petrochilos
  • Charles Burden
  • Kalpana Mahesh
  • Rachel Herstad
  • Georgey John
  • Hari Durga Tatineni
  • Rahul Agarwal
  • JASON, CRAWFORD MILLER
  • Ravi Raghunathan
  • Joseph Melendez

Assignees

  • REHRIG PACIFIC COMPANY

Dates

Publication Date
20260505
Application Date
20200131
Priority Date
20200128

Claims (10)

  1. CLAIMS What is claimed is: 1. A delivery method comprising: a) receiving an order for a plurality of Stock Keeping Units (SK Us); b) generating a pick sheet based upon the order for the plurality of SKUs; c) assembling a plurality of items based upon the pick sheet; d) imaging the assembled plurality of items to generate at least one image; e) analyzing the at least one image to identify the SK Us of the assembled plurality of items; f) electronically comparing the SKUs identified in step e) to the SKUs on the pick sheet; and g) indicating whether the SKUs identified in step e) match the SKUs on the pick sheet based upon the comparison in step f); wherein step e) includes: h) analyzing the at least one image to identify a package type of one of the plurality of items; i) based upon the identified package type from step h) narrowing a set of possible branding options to be identified; and j) after step i), determining a brand of the one of the plurality of items based upon the narrowed set of possible branding options.
  2. 2. The method of claim 1 wherein in step c ), the plurality of items are assembled on a pallet.
  3. 3. The method of claim 1 wherein step d) is performed by a camera mounted to a wrapper carrying wrap to be placed around the plurality of items. Date Re9ue/Date Received 2024-06-07
  4. 4. The method of claim 1 further including the steps of: k) imaging a new SKU to generate a plurality of images of the new SKU; and 1) adding the plurality of images of the new SKU to a database so that the new SKU can be identified in step e ).
  5. 5. A validation system comprising: a camera configured to generate at least one image of an item having an associated Stock Keeping Unit (SKU); and at least one computer compnsmg a computer readable medium storing computer executable instructions thereon that when executed by the at least one computer: a) analyze the at least one image to identify a package type of the item; b) based upon the identified package type from step a) identifying a subset of possible brands of the item; c) determine a branding of the item based upon the identified subset of brands and by analyzing the at least one image; d) identify the associated SKU of the item based upon steps a) and c); and e) electronically comparing the SKU identified in step c) to a pick sheet.
  6. 6. The validation system of claim 5 wherein the at least one computer includes a-at least one machine learning model trained on images of cases of beverage containers of a plurality of available package types including the package types of the item and of a plurality of available brands including the brand of the item.
  7. 7. The validation system of claim 6 wherein the item is a crate of beverage containers. 26 Date Re9ue/Date Received 2024-06-07
  8. 8. A validation system comprising: at least one computer comprising a computer readable medium storing computer executable instructions thereon that when executed by the at least one computer perform the steps of: a) receiving a pick sheet for a plurality of Stock Keeping Units (SKUs ), wherein each SKU has an associated package type and an associated branding; b) receiving a plurality of images of an item, including a first image and a second image, wherein the first image and second image are taken of different sides of the item; c) analyzing the first image to identify the item at a first confidence level; d) analyzing the second image to identify the item at a second confidence level; e) determining a SKU associated with the item based upon a higher of the first confidence level or the second confidence level; and f) electronically comparing the SKU determined in step e) to the plurality of SKUs on the pick sheet.
  9. 9. The system of claim 8 wherein the item is a crate of beverage containers.
  10. 10. The system of claim 8 wherein the at least one computer includes a machine learning model trained with images of crates of beverage containers. 27 Date Re9ue/Date Received 2024-06-07

Description

DELIVERY SYSTEM BACKGROUND PCT/0S2020/016007 [0001] The delivery of products to stores from distribution centers has many steps that are subject to errors and inefficiencies. When the order from the customer is received, at least one pallet is loaded with the specified products according to a "pick list." [0002] For example, the products may be cases of beverage containers (e.g. cartons of cans and beverage crates containing bottles or cans, etc). There are many different permutations of flavors, sizes, and types of beverage containers delivered to each store. When building pallets, missing or mis-picked product can account for significant additional operating costs. [0003] The loaded pallet(s) are then loaded on a truck, along with pallets for other stores. Misloaded pallets cause significant time delays to the delivery route since the driver will have to rearrange the pallets during the delivery process with potentially limited space in the trailer to maneuver. Extra pallets on trucks can also cause additional loading times to find the errant pallet and re-load it on the correct trailer [0004] At the store, the driver unloads the pallet( s) designated for that location. Drivers often spend a significant amount of time waiting in the store for a clerk to become available to check in the delivered product by physically counting it. During this process the clerk ensures that all product ordered is being delivered. The driver and clerk often break down the pallet and open each case to scan one UPC from every unique flavor and size. After the unique flavor and size is scanned, both the clerk and driver count the number of cases or bottles for that UPC. This continues until all product is accounted for on all the pallets. Clerks are typically busy 1 WO 2020/176196 PCT/0S2020/016007 helping their own customers which forces the driver to wait until a clerk becomes available to check-in product. SUMMARY [0005] The improved delivery system provides improvements to several phases of the delivery process. Although these improvements work well when practiced together, fewer than all, or even any one of these improvements could be practiced alone to some benefit. [0006] The improved delivery system facilitates order accuracy from the warehouse to the store by combining machine learning and computer vision software with a serialized (RFID/Barcode) shipping pallet. Pallet packing algorithms are based on the product mix and warehouse layout. [0007] Electronic order accuracy checks are done while building pallets, loading pallets onto trailers and delivering pallets to the store. When building pallets, the delivery system validates the build to ensure the correct product SKUs are being loaded on the correct pallet according to the pick list. Once the pallet is built the overall computer vision sku count for that specific pallet is compared against the pick list for that specific pallet to ensure the pallet is built correctly. This may be done prior to the pallet being stretch wrapped thus mitigating the cost of unwrapping of the pallet to audit and correct. This also prevents shortages and overages at the delivery point thus preventing the driver from having to bring back excess or make additional trips to deliver missing product. [0008] An optimized queue system may then be used to queue and load pallets onto the trailer in the correct reverse-stop sequence (last stop is loaded onto the trailer first). An electronic visual control showing which pallet is to be loaded on which trailer will be visible to the loader, e.g: Loading pallet #3 on Dock #4 ... 2 WO 2020/176196 PCT/0S2020/016007 [0009] The system will also decrease the time for the receiver at the delivery point (e.g. store) to check-in the product through a combination of checks that build trust at the delivery point. This is done through conveyance of the computer vision images of the validated SKUs on the pallet before it left the warehouse and upon delivery to the store. This can be a comparison of single images or a deep machine learning by having the image at the store also electronically identify the product SKUs. Delivery benefits include significantly reducing costs associated with waiting and checking product in at the store level and a verifiable electronic ledger of what was delivered for future audit. [0010] The delivery system will utilize a mobile device that the driver or receiver will have that takes one or more still images of the pallet (for example, 4, i.e. 1 on each side). The image(s) can then be compared electronically to the control picture from the warehouse and physically by the clerk. The clerk can electronically sign off that all product SKUs are there against their pick list. Different levels of receipt will be available for the clerk to approve. Validation at the store can be simple pallet serial scan via RFID/Barcode and GPS coordinates against the delivery, pallet image compare and/or sku validation through a machine learning compute