Hitachi High-Tech Corporation

Masami Takano

Yasuhiro Yoshida

Masayoshi Ishikawa

Fumihiro Sasajima

Kazuhiro Ueda

Koichi Hayakawa

Kouichi Hayakawa

An objective of the present invention is to provide a system which can infer the cause of a recipe error and present a correction candidate for the recipe error. A recipe information presentation system or recipe error inference system according to the present invention: causes a learner to learn a correspondence between a recipe and an error originating from the recipe; and acquires from the learner an inference result as to whether the error occurs when a new recipe is used (refer to FIG.).

Recipe information presentation system and recipe error inference system

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.

Error factor estimation device and error factor estimation method

The present disclosure proposes a diagnostic system capable of properly identifying the cause of even an error for which multiple factors or multiple compound factors may be accountable. The diagnostic system according to the present disclosure is provided with a learning device for learning at least one of a recipe defining operations of an inspection device, log data describing states of the device, or specimen data describing characteristics of a specimen in association with error types of the device, and estimates the cause of the error by using the learning device (refer to FIG.).

Growing community of inventors

Tokyo, Japan

Masami Takano