Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
SORTING MODEL TRAINING METHOD AND APPARATUS FOR INTELLIGENT RECOMMENDATION, AND INTELLIGENT RECOMMENDATION METHOD AND APPARATUS
Document Type and Number:
WIPO Patent Application WO/2023/087667
Kind Code:
A1
Abstract:
The present disclosure relates to the technical fields of data processing and machine learning. Provided are a sorting model training method and apparatus for intelligent recommendation, and an intelligent recommendation method and apparatus. The sorting model training method comprises: acquiring first user data and first resource data of a target domain, and acquiring second user data and second resource data of a source domain; determining an implicit feature according to the first user data, the first resource data, the second user data and the second resource data; and training a sorting model on the basis of the implicit feature, wherein the sorting model is used for performing resource recommendation on a user in the target domain. In the technical solution of the present disclosure, source-domain data is introduced in the form of an implicit feature, such that a "negative migration" phenomenon caused by directly using the source-domain data as a training sample can be avoided, and a recommendation effect of applying a sorting model to resource recommendation can be improved.

Inventors:
WU XUECHAO (CN)
CAO QIAN (CN)
HE XIAOHUI (CN)
BAI YUNLONG (CN)
Application Number:
PCT/CN2022/096599
Publication Date:
May 25, 2023
Filing Date:
June 01, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
BEIJING BAIDU NETCOM SCI & TECH CO LTD (CN)
International Classes:
G06F16/9535; G06F16/9536; G06Q50/00
Foreign References:
CN114139052A2022-03-04
CN113312644A2021-08-27
CN110348968A2019-10-18
CN113569151A2021-10-29
CN112417298A2021-02-26
US20210110306A12021-04-15
Attorney, Agent or Firm:
CHINA SCIENCE PATENT & TRADEMARK AGENT LTD. (CN)
Download PDF: