公开(公告)号：US10679007B2

公开(公告)日：2020-06-09

申请号：US16117964

申请日：2018-08-30

Applicant: Intelligent Fusion Technology, Inc

Inventor： Bin Jia ,  Cailing Dong ,  Zhijiang Chen ,  Kuo-Chu Chang ,  Nichole Sullivan ,  Genshe Chen

IPC: G06F40/00 ,  G06F40/295 ,  G06N5/04 ,  G06F16/28 ,  G06F40/30 ,  G06F40/253 ,  G06F40/268

Abstract: A method for pattern discovery and real-time anomaly detection based on knowledge graph, comprising: based on a dataset including messages collected within a certain period, constructing a local knowledge graph (KG); applying a statistical relational learning (SRL) model to predict hidden relations between entities to obtain an updated local KG; from all SPO triples of the updated local KG, discovering a normalcy pattern that includes frequent entities, frequent relations, and frequent SPO triples; and in response to receiving streaming data from a message bus, extracting a plurality of entities, a plurality of relations, and a plurality of SPO triples, from the streaming data for comparison with the normalcy pattern using semantic distance, thereby determining whether there is an abnormal entity, relation, or SPO triple in the streaming data.

公开(公告)号：US11307541B2

公开(公告)日：2022-04-19

申请号：US16562657

申请日：2019-09-06

Applicant: INTELLIGENT FUSION TECHNOLOGY, INC.

Inventor： Bin Jia ,  Jiaoyue Liu ,  Huamei Chen ,  Genshe Chen ,  Kuo-Chu Chang ,  Thomas M. Clemons, III

IPC: G06N20/00 ,  G06K9/62 ,  G06N5/04 ,  G06N5/02 ,  G06N3/08 ,  G06Q10/06 ,  G05B13/02 ,  G06F40/10 ,  G06N7/00

Abstract: A decision support method for machinery control includes extracting entities and relations from information sources, and creating subject-predicate-object (SPO) triples. Each SPO triple includes a subject entity and an object entity, and a relation between the subject entity and the object entity. The method further includes constructing a knowledge graph (KG) based on the SPO triples. The KG includes a plurality of nodes corresponding to the entities, and a plurality of links corresponding to the relations between the entities. The method also includes predicting missing links between the nodes and adding the predicted links to the KG, and performing diagnostic and prognostic analysis using the KG, including analyzing plain text description of MCS situations to obtain relevant information concerning key components from the KG, recognizing sensor observations and component conditions to diagnose situations of other related components, and providing prognostics by analyzing the present trending/symptom in the MCS operating process.