US 12,033,114 B2
System and method for providing warehousing service
Ashok Balasubramanian, San Jose, CA (US); Harish Kumar Krishnasamy, San Francisco, CA (US); Dineshbabu Bhoopalan, Fremont, CA (US); Sureshkumar Karuppuchamy, San Jose, CA (US); Syed Musthafa Sikkander, San Jose, CA (US); Ravneet Kaur, San Jose, CA (US); Charles Douglas Watkins, San Jose, CA (US); and Balasubramanian Jayamani, San Jose, CA (US)
Assigned to EBAY INC., San Jose, CA (US)
Filed by eBay Inc., San Jose, CA (US)
Filed on Jul. 6, 2021, as Appl. No. 17/368,127.
Prior Publication US 2023/0010509 A1, Jan. 12, 2023
Int. Cl. G06Q 10/087 (2023.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06Q 30/0601 (2023.01)
CPC G06Q 10/087 (2013.01) [G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06Q 30/0621 (2013.01); G06Q 30/0639 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method comprising:
extracting, by a transaction extractor of a training component on a networking server, training data from past transactions, the training data including item attributes and transaction locations;
transmitting, by the transaction extractor, the extracted data to a training hardware module of the training component on the networking server;
training, by the training hardware module of the training component on the networking server, a machine learning model with the training data to identify probabilities of items selling in a plurality of transaction zones;
onboarding, by an onboarding engine of the networking server, warehouse space of a fulfillment partner, the onboarding comprising:
causing presentation of an onboarding user interface to the fulfillment partner;
receiving, via the onboarding user interface, size information for the warehouse space;
identifying location information for the fulfillment partner; and
persisting the warehouse space of the fulfillment partner with the size information and the location information to data storage;
receiving, by a warehousing engine on the networking server via a user interface, a warehouse request to warehouse inventory in a remote location;
in response to receiving the request, triggering an analysis hardware module of the networking server to determine at least one transaction zone based on item attributes of the inventory by applying the trained machine learning model to identify one or more transaction zones having highest probabilities;
based on the determined at least one transaction zone, determining, by a recommendation hardware module of the networking server, one or more warehouse spaces that satisfy a spacing requirement;
causing presentation, by the recommendation hardware module of the networking server, of a warehouse recommendation on a client device, the warehouse recommendation indicating the one or more warehouse spaces; and
periodically updating, by the training component of the networking server, the machine learning model by retraining on updated training data.