Search International and National Patent Collections

1. (WO2018198267) CAUSAL RELATIONSHIP LEARNING METHOD, PROGRAM, DEVICE, AND ABNORMALITY ANALYSIS SYSTEM

Pub. No.:    WO/2018/198267    International Application No.:    PCT/JP2017/016729
Publication Date: Fri Nov 02 00:59:59 CET 2018 International Filing Date: Fri Apr 28 01:59:59 CEST 2017
IPC: G05B 23/02
Applicants: NEC CORPORATION
日本電気株式会社
Inventors: FUJITSUKA, Masashi
藤塚 理史
Title: CAUSAL RELATIONSHIP LEARNING METHOD, PROGRAM, DEVICE, AND ABNORMALITY ANALYSIS SYSTEM
Abstract:
Provided are a method, program, and device with which a causal relationship can be learned with high accuracy in a deterministic system, as well as a system which performs abnormality analysis using a causal relationship. A causal relationship learning device according to one embodiment of the present invention comprises: a correlation determination unit that determines a correlation between measurement values measured by two sensors; and a low correlation causal relationship estimation unit that, if the correlation is lower than a predetermined reference, determines a causal relationship between the two sensors by estimating a measurement value which is the cause from a measurement value which is the effect.