Title:
TRANSFER RELATIONSHIP-BASED LOCAL ADAPTIVE KNOWLEDGE GRAPH OPTIMIZATION METHOD
Document Type and Number:
WIPO Patent Application WO/2020/177142
Kind Code:
A1
Abstract:
The present invention provides a transfer relationship-based local adaptive knowledge graph optimization method, comprising: setting a training sample set; setting that any ri and ei initially belong to a certain distribution; performing normalization; forming a new training sample set; initializing a triple set as a null set; setting a correct triple corresponding to a wrong triple, replacing the correct triple with a head entity or tail entity of the wrong triple to form an error training sample set, and incorporating the error training sample set into the triple set; obtaining an edge parameter of an entity; obtaining an edge parameter of a relationship; calculating a parameter where the edge parameter changes with the entity and the relationship; obtaining a new loss function based on a transfer relationship; and performing determination and optimizing each entity or relationship vector by using a stochastic gradient descent (SGD) function. According to the present invention, the incompleteness of data can be made up, different potential semantics between the relationship and the entity can be better expressed, and the new knowledge map constructed after the optimization has higher accuracy.
Inventors:
WANG DALING (CN)
LIU HONGCHEN (CN)
FENG SHI (CN)
ZHANG YIFEI (CN)
LIU HONGCHEN (CN)
FENG SHI (CN)
ZHANG YIFEI (CN)
Application Number:
PCT/CN2019/077728
Publication Date:
September 10, 2020
Filing Date:
March 12, 2019
Export Citation:
Assignee:
UNIV NORTHEASTERN (CN)
International Classes:
G06F16/36
Foreign References:
| CN105824802A | 2016-08-03 | |||
| CN108959328A | 2018-12-07 | |||
| CN108446769A | 2018-08-24 | |||
| US20190057310A1 | 2019-02-21 | |||
| CN109063021A | 2018-12-21 | |||
| CN107391677A | 2017-11-24 | |||
| CN107784088A | 2018-03-09 |
Attorney, Agent or Firm:
SHENYANG DONGDA INTELLECTUAL PROPERTY AGENCY CO., LTD (CN)
Download PDF: