公开(公告)号：US11681756B2

公开(公告)日：2023-06-20

申请号：US16944761

申请日：2020-07-31

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yuwon Lee ,  Hwangki Min ,  Sungmin Rhee ,  Shunghyun Choi

IPC: G06F16/9032 ,  G06F16/9038 ,  G06F16/906 ,  G06F40/30

CPC classification number: G06F16/90332 ,  G06F16/906 ,  G06F16/9038 ,  G06F40/30

Abstract: An electronic device includes a memory configured to store a plurality of types of user data, and a processor configured to be operatively connected to the memory, wherein the processor is configured to generate an embedding vector through text embedding using first text data which is included in the user data and is related to content of the user data for each type of the user data; calculate a weight for the embedding vector using information which is included in the user data and is related to usability of the user data for each type of the user data; when a query is input, generate a query vector through the text embedding using second text data included in the query; and quantify user interest in the query for each type of the user data based on the embedding vector, the weight for the embedding vector, and the query vector.

公开(公告)号：US11463539B2

公开(公告)日：2022-10-04

申请号：US17136953

申请日：2020-12-29

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sungmin Rhee ,  Sungdeuk Park

IPC: H04L29/08 ,  H04L67/306 ,  G06K9/62 ,  G06N20/00 ,  H04L67/10

Abstract: An electronic device that includes a communication module and a processor operatively connected to the communication module to exchange data with an external electronic device through the communication module is provided. The processor generates user data and a user profile based on collected user information related to a plurality of items, receive learning information data related to the plurality of items from the external electronic device, generate user learning data by applying the learning information data to the user data, learn a user preference pattern based on the user learning data, update the user profile based on the learned user preference pattern, and receive recommended item data from the external electronic device based on the updated user profile.