Title:
MARKETING PRODUCT RECOMMENDATION METHOD
Document Type and Number:
WIPO Patent Application WO/2019/165872
Kind Code:
A1
Abstract:
Provided is a marketing product recommendation method, comprising: after receiving a user's request for marketing product data, acquiring the user features of the user and the product features of each marketing product; generating overlapping features based on the user features and the product features; inputting the user features, the product features and the overlapping features into a click-rate evaluation model to obtain a click-rate evaluation value of the user for each marketing product, wherein the click-rate evaluation model is a machine learning model, and is trained by using user features and marketing product feature samples with a known click rate; and determining, according to the click rate evaluation value, the M marketing products, and returning data of the M marketing products to the user, wherein M is a natural number.
Inventors:
WANG YI (CN)
Application Number:
PCT/CN2019/073610
Publication Date:
September 06, 2019
Filing Date:
January 29, 2019
Export Citation:
Assignee:
ALIBABA GROUP HOLDING LTD (CN)
International Classes:
G06Q30/02
Foreign References:
CN106295832A | 2017-01-04 | |||
CN108416625A | 2018-08-17 | |||
CN106485562A | 2017-03-08 | |||
CN107705183A | 2018-02-16 | |||
CN105528374A | 2016-04-27 |
Attorney, Agent or Firm:
BEIJING BESTIPR INTELLECTUAL PROPERTY LAW CORPORATION (CN)
Download PDF: