Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
PREDICTION APPARATUS, PREDICTION METHOD, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2021/157670
Kind Code:
A1
Abstract:
The present invention constructs a regression model reflecting a causal relationship between variation of an explanatory variable and variation of a response variable. This prediction apparatus predicts a characteristic value of a product using process data obtained from production equipment. Further, the prediction apparatus comprises: a process data acquisition unit that reads out the process data from a storage device storing the process data obtained from the production equipment; and a prediction model generation unit that generates a prediction model that has learned features of the process data obtained from the production equipment on the basis of causal relationship information that defines a combination of first process data using a predetermined explanatory variable and second process data using a response variable thereof or a value corresponding to the second process data, included in the read-out process data. The prediction model generation unit generates a prediction model such that the positive/negative variation direction of the response variable is determined in accordance with the positive/negative variation direction of the explanatory variable.

More Like This:
WO/2012/005408SYSTEM AND METHOD FOR SAVING MARINE FUEL BY OPTIMIZING ENERGY EFFICIENCY FOR OPTIMALLY SAILING A SHIP, AND RECORDING MEDIUM FOR RECORDING A COMPUTER PROGRAM FOR IMPLEMENTING THE METHOD
JP6630846Prediction method for the abundance of pelagic squid resources based on the gray system
WO/2018/099220METHOD AND DEVICE FOR PREDICTING PLANT DISEASES AND PESTS IN PLANTER
Inventors:
OKAMOTO HIROSHI (JP)
TAKAHASHI MARINA (JP)
SHINOHARA SHUJI (JP)
MITSUYOSHI SHUNJI (JP)
HAITSUKA MASAHIRO (JP)
KOZONO HIDETOSHI (JP)
MIYOSHI FUMIHIRO (JP)
Application Number:
PCT/JP2021/004179
Publication Date:
August 12, 2021
Filing Date:
February 04, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
DAICEL CORP (JP)
International Classes:
G06Q10/04; G06Q50/04
Domestic Patent References:
WO2012093483A12012-07-12
Foreign References:
JP2019074969A2019-05-16
JP2009020787A2009-01-29
JP2001325582A2001-11-22
JP2011058102A2011-03-24
JP6477423B22019-03-06
JP5751045B22015-07-22
JP2018120343A2018-08-02
JP2001106703A2001-04-17
Other References:
KURAHASHI, SETSUYA; TERANO, TAKAO: "Data Mining from Plant Process Time Series by a Learning Classifier System", JSAI TECHNICAL REPORT, SIG-KBS, vol. SIG-KBS-A201-01, no. 56, 17 May 2002 (2002-05-17), Japan, pages 1 - 6, XP009541207, ISSN: 2436-4592
See also references of EP 4102421A4
Attorney, Agent or Firm:
IP FIRM SHUWA (JP)
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: REGRESSION ANALYSIS DEVICE, REGRESSION ANALYSIS METHOD, AND PROGRAM

Next Patent: COPOLYMER