US 12,248,948 B1
System and method of integrating social trends in assortment planning
Machiraju Pakasasana Rama Rao, Hyderabad (IN); Arun Raj Parwana Adiraju, Hyderabad (IN); Abhinav Kishore, Hyderabad (IN); Vineet Chaudhary, Hyderabad (IN); Pawan Singh, Hyderabad (IN); Ankit Goel, Uttar Pradesh (IN); and Vaibhav Sharma, Hyderabad (IN)
Assigned to Blue Yonder Group, Inc., Scottsdale, AZ (US)
Filed by JDA Software Group, Inc., Scottsdale, AZ (US)
Filed on Apr. 23, 2019, as Appl. No. 16/392,080.
Claims priority of provisional application 62/678,544, filed on May 31, 2018.
Int. Cl. G06Q 30/0201 (2023.01); G06F 16/9536 (2019.01); G06N 3/08 (2023.01); G06Q 10/087 (2023.01)
CPC G06Q 30/0201 (2013.01) [G06F 16/9536 (2019.01); G06N 3/08 (2013.01); G06Q 10/087 (2013.01)] 20 Claims
OG exemplary drawing
 
8. A computer-implemented method, comprising:
receiving, using a computer comprising a processor and a memory, an initial set of images as image data from an imaging sensor;
transforming analog image values from each image of the initial set of images via a RGB model to digital image values wherein each pixel of each image is identified as a value corresponding to a red channel, a value corresponding to a green channel and a value corresponding to a blue channel;
storing each of the transformed initial set of images as digital RGB data in a three-dimensional matrix;
learning by a neural network model using unsupervised learning to identify one or more product categories and one or more product attributes based on at least the digital image values;
identifying, using the computer, one or more attribute values from the digital image values using the learned neural network model;
quantifying, using the computer, a social affinity score of one or more items based on recentness, relevance, and similarities of the identified one or more attribute values to an attribute value of a potential product for a product assortment; and
updating, using the computer, the learning of the neural network model to identify at least one additional product attribute based, at least in part, on one or more additional images indicating an updated trend on a social media feed.