Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
SEARCH RECOMMENDATION MODEL TRAINING METHOD, AND SEARCH RESULT SORTING METHOD AND DEVICE
Document Type and Number:
WIPO Patent Application WO/2021/233199
Kind Code:
A1
Abstract:
A search recommendation model training method, and a search result sorting method and device. The training method comprises: obtaining a training sample set, which comprises a sample user behavior group sequence and a sample covering user behavior group sequence; and obtaining an object of a response operation of the sample user subjected to covering processing by using the training sample set as input data, and using the object as a training target to train a search recommendation model to obtain a trained search recommendation model, wherein the search recommendation model is used for, when a target user inputs a query field, predicting a tag corresponding to a candidate recommendation object in the search result corresponding to the query field; the tag is used for denoting the probability that the target user performs a response operation on the candidate recommendation object. The technical solution based on the method can improve the accuracy of the search recommendation model, thereby improving the user experience.

Inventors:
CAI GUOHAO (CN)
WANG GANG (CN)
DONG ZHENHUA (CN)
LI XIAOGUANG (CN)
HE XIUQIANG (CN)
ZHU HONG (CN)
Application Number:
PCT/CN2021/093618
Publication Date:
November 25, 2021
Filing Date:
May 13, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
G06F16/9535
Foreign References:
CN106156023A2016-11-23
CN103226569A2013-07-31
CN103488764A2014-01-01
CN109426826A2019-03-05
EP3647987A12020-05-06
CN202010424719A2020-05-19
Attorney, Agent or Firm:
LONGSUN LEAD IP LTD. (CN)
Download PDF: