Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
ENTITY PAIR RECOGNITION METHOD AND APPARATUS SPANNING GRAPH DATA AND RELATIONAL DATA
Document Type and Number:
WIPO Patent Application WO/2023/168659
Kind Code:
A1
Abstract:
Provided in the embodiments of the present invention are an entity pair recognition method and apparatus spanning graph data and relational data. The method comprises: acquiring target relational data and target first graph data which are to be subjected to extraction, wherein the target relational data comprises at least one tuple, and the target first graph data comprises at least one first node; generating corresponding second graph data according to the target relational data, wherein the second graph data comprises at least one second node, and the first tuple corresponds to the second node; and according to the first node and the second node, determining an entity pair which corresponds to a match in the target first graph data and the target relational data. Entity recognition is studied by means of spanning relational data and graph data, rather than only performing entity recognition on relational data; and matches found by means of parameter simulation are interpretable, and why two vertex matches are based on a matching vertex pair and a cumulative score is explained.

Inventors:
FAN WENFEI (CN)
JIN RUOCHUN (CN)
LU PING (CN)
YU WENYUAN (CN)
Application Number:
PCT/CN2022/080180
Publication Date:
September 14, 2023
Filing Date:
March 10, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
SHENZHEN INST OF COMPUTING SCIENCES (CN)
International Classes:
G06F16/22; G06F40/279; G06F16/28; G06F40/30; G06N3/04
Foreign References:
CN112632226A2021-04-09
CN111209409A2020-05-29
CN112988877A2021-06-18
CN114048329A2022-02-15
US10268735B12019-04-23
Attorney, Agent or Firm:
ZHISHENG & ASSOCIATES (CN)
Download PDF: