Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD AND APPARATUS FOR PRODUCT RECOMMENDATION IN OFFLINE STORE ON BASIS OF FEDERATED LEARNING
Document Type and Number:
WIPO Patent Application WO/2022/054983
Kind Code:
A1
Abstract:
The present disclosure discloses an operation method of a client and a server in a store management system, and an apparatus supporting same. An operation method of a client in a store management system, according to one embodiment of the present disclosure, may comprise the steps of: receiving, from a server, information on a global model of a product recommendation system; generating a local model of a client on the basis of the global model; determining placement in an offline store of a plurality of products from among products offered in the offline store on the basis of the local model; updating the local model on the basis of preference and non-preference of each of the plurality of products; and transmitting, to the server, information of the updated local model.

Inventors:
PARK JAE YONG (KR)
KIM SUNGJIN (KR)
KIM ILHWAN (KR)
OH JAEKY (KR)
Application Number:
PCT/KR2020/012184
Publication Date:
March 17, 2022
Filing Date:
September 09, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
LG ELECTRONICS INC (KR)
International Classes:
G06Q30/06; G06F16/33; G06F17/18
Foreign References:
KR20200002034A2020-01-07
JP2019101861A2019-06-24
KR20170082294A2017-07-14
KR20190106347A2019-09-18
JP2020009157A2020-01-16
Attorney, Agent or Firm:
SUNG, Byung Kee (KR)
Download PDF: