Title:
RECOMMENDATION METHOD, RECOMMENDATION MODEL TRAINING METHOD, AND RELATED PRODUCT
Document Type and Number:
WIPO Patent Application WO/2023/011382
Kind Code:
A1
Abstract:
Embodiments of the present application provide a recommendation method, a recommendation model training method, and a related product. The recommendation method comprises: obtaining data to be predicted; obtaining a plurality of target reference samples from a plurality of reference samples according to the similarity between the data and the plurality of reference samples, each reference sample and the data both comprising user feature domain data and article feature domain data, the user feature domain data of the data being used for indicating a target user feature, the article feature domain data of the data being used for indicating a target article feature, and each target reference sample and the data having the user feature domain data and/or the article feature domain data which are partially identical; obtaining target feature information of the data according to the plurality of target reference samples and the data; obtaining an output value by using the target feature information as an input by means of a deep neural network (DNN); and determining, according to the output value, whether to recommend a target article to the target user. The embodiments of the present application improve the recommendation accuracy.
Inventors:
GUO WEI (CN)
QIN JIARUI (CN)
TANG RUIMING (CN)
LIU ZHIRONG (CN)
HE XIUQIANG (CN)
ZHANG WEINAN (CN)
YU YONG (CN)
QIN JIARUI (CN)
TANG RUIMING (CN)
LIU ZHIRONG (CN)
HE XIUQIANG (CN)
ZHANG WEINAN (CN)
YU YONG (CN)
Application Number:
PCT/CN2022/109297
Publication Date:
February 09, 2023
Filing Date:
July 30, 2022
Export Citation:
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
G06F16/9535
Domestic Patent References:
| WO2021081962A1 | 2021-05-06 |
Foreign References:
| CN113722583A | 2021-11-30 | |||
| CN111259263A | 2020-06-09 | |||
| CN109299396A | 2019-02-01 | |||
| CN111881363A | 2020-11-03 | |||
| CN112632403A | 2021-04-09 | |||
| US20200272913A1 | 2020-08-27 | |||
| CN202110877429A | 2021-07-31 |
Other References:
XUE FENG, LIU KAI; WANG DONG; ZHANG HAOBO: "Personalized Recommendation Algorithm Based on Deep Neural Network and Weighted Implicit Feedback", PATTERN ＲECOGNITION AND ARTIFICIAL INTELLIGENCE, vol. 33, no. 4, 1 April 2020 (2020-04-01), pages 295 - 302, XP093033460, ISSN: 1003-6059, DOI: 10.16451/j.cnki.issn1003-6059.202004002
Attorney, Agent or Firm:
SCIHEAD IP LAW FIRM (CN)
Download PDF:
Previous Patent: DATA PROCESSING METHOD AND APPARATUS
Next Patent: COPOLYMER, AND PREPARATION METHOD THEREFOR AND USE THEREOF
Next Patent: COPOLYMER, AND PREPARATION METHOD THEREFOR AND USE THEREOF