Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
ERROR CAUSE ESTIMATION DEVICE AND ESTIMATION METHOD
Document Type and Number:
WIPO Patent Application WO/2022/059135
Kind Code:
A1
Abstract:
An error cause estimation device comprising: a data pre-processing unit that uses data to be processed and generates training data that has an appropriate format for input to a machine learning model; and a model tree generation unit that generates error detection models that are training models for detecting errors and uses the training data as inputs therefor, and generates a model tree that expresses the relationship between error detection models by using a tree structure that has the error detection models as node therefor. Thus, it is possible to generate a training model that detects errors for each of a plurality of types of errors that occur, even when there has been no prior annotation of error causes.

Inventors:
YOSHIDA YASUHIRO (JP)
ISHIKAWA MASAYOSHI (JP)
SASAJIMA FUMIHIRO (JP)
TAKANO MASAMI (JP)
HAYAKAWA KOICHI (JP)
Application Number:
PCT/JP2020/035274
Publication Date:
March 24, 2022
Filing Date:
September 17, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
HITACHI HIGH TECH CORP (JP)
International Classes:
G06N20/00
Other References:
HIROTOMO HAYASHI ; QIANGFU ZHAO: "Model reduction of neural network trees based on dimensionality reduction", NEURAL NETWORKS, 2009. IJCNN 2009. INTERNATIONAL JOINT CONFERENCE ON, IEEE, PISCATAWAY, NJ, USA, 14 June 2009 (2009-06-14), Piscataway, NJ, USA , pages 1171 - 1176, XP031498245, ISBN: 978-1-4244-3548-7
HAYASHI, HIROTOMO ET AL.: "A Fast Algorithm for Inducing Neural Network Trees", IPSJ JOURNAL, vol. 49, no. 8, 15 August 2008 (2008-08-15), pages 2878 - 2889, ISSN: 1882-7837
"SETO, YOICHI et al.", 25 July 2016, JAPAN INDUSTRIAL PUBLISHING CO.,, Tokyo, ISBN: 978-4-8190- 2808-0, pages: 68 - 83
Attorney, Agent or Firm:
POLAIRE I.P.C. (JP)
Download PDF: