Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Sunday 05.04.2020 at 10:00 AM CEST
Settings

Settings

1. WO1996005555 - CAUSE INFERRING DEVICE

Publication Number WO/1996/005555
Publication Date 22.02.1996
International Application No. PCT/JP1995/001086
International Filing Date 02.06.1995
Chapter 2 Demand Filed 31.10.1995
IPC
G06N 5/02 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
02Knowledge representation
CPC
G06N 5/025
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
02Knowledge representation
025Extracting rules from data
Applicants
  • KOMATSU LTD. [JP/JP]; 3-6, Akasaka 2-chome Minato-ku Tokyo 107, JP (AllExceptUS)
  • MINOBE, Kaori [JP/JP]; JP (UsOnly)
  • YAMAGUCHI, Hiroyoshi [JP/JP]; JP (UsOnly)
Inventors
  • MINOBE, Kaori; JP
  • YAMAGUCHI, Hiroyoshi; JP
Agents
  • KIMURA, Takahisa; 6F, Sendai Building 8-11, Minato 1-chome Chuo-ku Tokyo 104, JP
Priority Data
6/18741209.08.1994JP
Publication Language Japanese (JA)
Filing Language Japanese (JA)
Designated States
Title
(EN) CAUSE INFERRING DEVICE
(FR) DISPOSITIF D'INFERENCE DE CAUSES
Abstract
(EN)
A cause inferring device which infers causes with improved accuracy and efficiency. A phenomenon item (F) other than phenomenon items (A, B and C) for which frequency-of-occurrence data are already inputted is selected based on the correlation data regarding cause items (2, 3 and 4) having the highest certainty among cause items (1-5) whose certainties are calculated. The frequency-of-occurrence data of the selected phenomenon item (F) and already inputted frequency-of-occurrence data are inputted again and the certainties of the cause items are computed. By repeating such selection and arithmetic processing at least once, causes are narrowed down as a final inference.
(FR)
L'invention concerne un dispositif d'inférence de causes qui infère les causes avec une précision et une efficacité améliorées. On choisit l'élément de phénomène (F) autre que les éléments de phénomènes (A, B et C) pour lesquels on avait déjà entré des données de fréquence d'occurrence, sur la base des données de corrélation relatives aux éléments causals (2, 3 et 4) ayant la certitude la plus élevée parmi les éléments causals (1-5) dont on avait calculé les certitudes. On entre à nouveau les données de fréquence d'occurence de l'élément de phénomène choisi (F) et les données de fréquence d'occurrence déjà entrées et on calcule les certitudes des éléments causals. En répétant encore au moins une fois cette sélection et le traitement arithmétique, on rétrécit les causes jusqu'à une inférence finale.
Also published as
Latest bibliographic data on file with the International Bureau