Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
LEARNING METHOD OF AI MODEL AND ELECTRONIC APPARATUS
Document Type and Number:
WIPO Patent Application WO/2021/020810
Kind Code:
A1
Abstract:
Disclosed are a training method of an artificial intelligence (AI) model configured to provide information identifying a recommendation item and a recommended user, and an electronic apparatus for training an AI model. The training method includes obtaining user data and item data; generating a first semantic vector at a first time interval based on the user data; generating a second semantic vector at the first time interval based on the item data; generating a vector that represents a relevance between the first semantic vector and the second semantic vector at the first time interval; storing data corresponding to the generated vector, the first semantic vector, and the second semantic vector; and obtaining an updated weight for the first AI model by training the first AI model based on the stored data.

Inventors:
KO KWANGWON (KR)
PARK JONGCHUL (KR)
Application Number:
PCT/KR2020/009742
Publication Date:
February 04, 2021
Filing Date:
July 23, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G06N3/08; G06N3/04; G06Q50/10
Foreign References:
US20180342004A12018-11-29
KR101997222B12019-07-05
US20180075137A12018-03-15
CN109885756A2019-06-14
CN108563755A2018-09-21
US20180342004A12018-11-29
Other References:
NARANG SHIPRA ET AL.: "2018 International Conference on Advances in Computing", 12 October 2018, IEEE, article "Deep Content-Collaborative Recommender System (DCCRS", pages: 110 - 116
ELKAHKY ALI MAMDOUH ET AL.: "The Science of Security", 18 May 2015, ACM, article "A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems", pages: 278 - 288
See also references of EP 3953869A4
Attorney, Agent or Firm:
KIM, Tae-hun et al. (KR)
Download PDF: