Title:
MACHINE LEARNING BASED NETWORK MODEL CONSTRUCTION METHOD AND APPARATUS
Document Type and Number:
WIPO Patent Application WO/2017/206936
Kind Code:
A1
Abstract:
A machine learning based network model construction method and apparatus. The method comprises: acquiring a data processing flow of an original network model and a reference data set generated by the original network model in the data processing flow (S101); according to the data processing flow and the reference data set, hierarchically constructing at least one sub-network (S102); using the reference data set to perform optimization training on the at least one sub-network (S103); and combining and processing the at least one sub-network after the optimization training to form a target network model (S104). The technical solution can simplify a construction process of a network model, thereby improving the model construction efficiency.
Inventors:
ZHENG BO (CN)
LIU ZHIBIN (CN)
LIU RIJIA (CN)
CHEN QIAN (CN)
LIU ZHIBIN (CN)
LIU RIJIA (CN)
CHEN QIAN (CN)
Application Number:
PCT/CN2017/086917
Publication Date:
December 07, 2017
Filing Date:
June 02, 2017
Export Citation:
Assignee:
TENCENT TECH SHENZHEN CO LTD (CN)
International Classes:
G06N3/08
Foreign References:
CN106096727A | 2016-11-09 | |||
CN104751227A | 2015-07-01 | |||
CN103729459A | 2014-04-16 | |||
CN101814160A | 2010-08-25 | |||
EP2533176A1 | 2012-12-12 |
Other References:
See also references of EP 3467723A4
Attorney, Agent or Firm:
DEQI INTELLECTUAL PROPERTY LAW CORPORATION (CN)
Download PDF:
Previous Patent: SYSTEM AND METHOD FOR AUDIO AND VIDEO SYNCHRONIZATION TEST
Next Patent: METHOD AND DEVICE FOR INFORMATION PROCESSING
Next Patent: METHOD AND DEVICE FOR INFORMATION PROCESSING