Digitization of a catalog of retail products

• US 9,928,530 B2
• Filed: 01/19/2017
• Issued: 03/27/2018
• Est. Priority Date: 04/21/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Krishnan, Nagesha Rao, Ponniah, Anbumunee, Prasada, Soumya, Sar, Sudhanshu S.
• Primary Examiner(s): Stopp, Courtney L
• Application Number:
  US15/409,579
• Publication Number:
  US 20170308939A1
• Time in Patent Office: 432 Days
• Field of Search: None
• CPC Class Codes: G06Q 30/0603 Catalogue ordering
• CPC Class Codes: G06Q 30/0629 for generating comparisons
• CPC Class Codes: G06Q 30/0643 Graphical representation of items or shoppers

Abstract

Embodiments of the present invention disclose a method, computer program product, and system for catalog digitization. A method including receiving observed information including physical attributes of a plurality of products, assigning an importance to each physical attribute, organizing the products into product categories based on the physical attributes and their corresponding importance, determining a product profile for of the products based on the product category of each of the products and a likelihood of any two attributes being observed together with respect to each of the products, identifying a match between two products based on a similarity between the physical attributes of the two products and their corresponding importance, and a comparison between the product profiles of the two products, preparing a product description based on a combination of the physical attributes of the two matching products, and creating a digital product catalog comprising the product description.

Claims

1. A method for catalog digitization of a plurality of products in a shop, the method comprising:

receiving captured photographs of the plurality of products from a camera mounted in the shop;

receiving captured video of the plurality of products from a video camera mounted in the shop, wherein the captured video comprises photographs and audio;

generating a set of descriptions from the captured photographs by extracting physical attributes from the captured photographs and the captured video using image recognition technology, and from the captured audio from the captured video using voice recognition software, wherein the physical attributes are selected from a group consisting of a dimension, a shape, a weight, a color, a price, a location in the store, and words spoken when someone is holding or pointing to each product of the plurality of products;

assigning an importance value to each physical attribute based on a likelihood of each physical attribute positively identifying a product;

organizing the set of descriptions into product categories based on the physical attributes of each description of the set of descriptions and their corresponding importance value, wherein a importance value is dependent on a product category;

combining one or more groups of one or more descriptions of the set of descriptions into one or more product descriptions, based on multiple iterations of comparison of each physical attribute of each description of the set of descriptions, the product category of each description of the set of descriptions, a likelihood of any two physical attributes of each description of the set of descriptions being observed together, on the importance value of each physical attribute of each description of the set of descriptions, calculation of a confidence score of a match between one or more groups of one or more descriptions of the set of descriptions, and comparing the confidence score to a predetermined confidence threshold,

wherein the importance value of each physical attribute is updated on each iteration of comparison of each physical attribute of each set of descriptions, wherein the likelihood of each physical attribute positively identifying a product increases with each iteration of multiple iterations of comparison, wherein the confidence score is based on the physical attributes of each of the one or more groups of one or more descriptions of the set of descriptions and their corresponding importance value, and the confidence threshold is determined by an administrator;

determining a product profile for each of the of the one or more product descriptions based on the corresponding one or more groups of the one or more descriptions of the set of descriptions;

creating a digital product catalog comprising the one or more product profiles; and

publishing the digital catalog on-line.