Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
ARTIFICIAL INTELLIGENCE-BASED FAULT NODE IDENTIFICATION METHOD, DEVICE, APPARATUS, AND MEDIUM
Document Type and Number:
WIPO Patent Application WO/2021/114613
Kind Code:
A1
Abstract:
Provided is an artificial intelligence-based fault node identification method, relating to the field of artificial intelligence, comprising: obtaining graph data corresponding to a faulty system, the graph data comprising an invocation relationship among a plurality of nodes in the faulty system; obtaining the node data of each node in the faulty system; determining each alarm node according to the node data of each node, and according to each alarm node and invocation relationship, obtaining an initial detection result that each alarm node in the faulty system is a fault node; according to the invocation relationship among the plurality of nodes, grouping the alarm nodes to obtain a combination of the alarm nodes; according to the combination of alarm nodes and the initial detection result of the alarm nodes, determining a fault node in each alarm node combination. At the same time, the present application also relates to blockchain technology, and the graph data and the node data can all be stored on the blockchain.

Inventors:
CHEN ZHENBO (CN)
ZHENG LIYING (CN)
XU LIANG (CN)
Application Number:
PCT/CN2020/098772
Publication Date:
June 17, 2021
Filing Date:
June 29, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
PING AN TECH SHENZHEN CO LTD (CN)
International Classes:
G06F16/27; G06F11/30; G06N3/04; G06N3/08
Foreign References:
CN110134539A2019-08-16
CN109756376A2019-05-14
CN109740025A2019-05-10
CN107222339A2017-09-29
US20200021607A12020-01-16
Attorney, Agent or Firm:
ADVANCE CHINA IP LAW OFFICE (CN)
Download PDF: