Invention Application
- Patent Title: METHOD FOR DEVELOPING MACHINE-LEARNING BASED TOOL
-
Application No.: US17064692Application Date: 2020-10-07
-
Publication No.: US20220107788A1Publication Date: 2022-04-07
- Inventor: Ariel BECK , Chandra Suwandi WIJAYA
- Applicant: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.
- Applicant Address: JP Osaka
- Assignee: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.
- Current Assignee: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.
- Current Assignee Address: JP Osaka
- Main IPC: G06F8/34
- IPC: G06F8/34 ; G06F16/245 ; G06N20/00 ; G06Q10/10 ; G06Q10/06 ; G06T7/00 ; G06T7/30 ; G06K9/62 ; G06K9/46 ; G06K9/20

Abstract:
A method for developing machine-learning (ML) based tool including initializing an input dataset, which is pre-processed by a first model to harmonize the dataset. Historical data similar to the input data set is fetched from a historical database. Based thereupon a controller recommends a method and a control-setting associated with the identified model for the visual inspection process to a user. Thereafter, the dataset is annotated by a second model to define a labelled data set. A plurality of features are extracted with respect to the data set through a feature extractor. A machine-learning classifier operates upon the extracted features and classifies the dataset with respect to one or more labels. A meta controller communicates with one or more of the first model, the second model, the feature extractor and the selected classifier for assessing a performance of at least one of first model and the feature extractor.
Public/Granted literature
- US11568318B2 Method for developing machine-learning based tool Public/Granted day:2023-01-31
Information query