Systems and methods for configuring test parameters in machine learning evaluation
AssigneeWoven By Toyota, Inc.
InventorsDaisuke HASHIMOTO, Eiji Nakatsugawa, Suigen Koide
Life of this patent
Estimating the term…
Abstract
Provided are a method, system, and device for configuring test parameters used in evaluating a machine learning (ML) model. The method may include: obtaining a user input comprising at least one test parameter; storing the obtained user input in a requirement as code (RAC) file; interpreting, by a requirement management interface, at least one test parameter from the RAC file; and evaluating the ML model based on the interpreted at least one test parameter from the RAC file.
Claims20
A method for configuring test parameters used in evaluating a machine learning (ML) model, the method comprising:
- obtaining a user input comprising at least one test parameter;
- storing the obtained user input in a requirement as code (RAC) file;
- interpreting, by a requirement management interface, at least one test parameter from the RAC file;
- and
- evaluating the ML model based on the interpreted at least one test parameter from the RAC file.
An apparatus for configuring test parameterse used in evaluating a machine learning (ML) model, the apparatus comprising:
- at least one memory storing computer-executable instructions;
- and
- at least one processor configured to execute the computer-executable instructions to:
- obtain a user input comprising at least one test parameter;
- store the obtained user input in a requirement as code (RAC) file;
- interpret, by a requirement management interface, at least one test parameter from the RAC file;
- and
- evaluate the ML model based on the interpreted at least one test parameter from the RAC file.
A non-transitory computer-readable recording medium having recorded thereon instructions executable by at least one processor to cause the processor to perform a method comprising:
- obtaining a user input comprising at least one test parameter;
- storing the obtained user input in a requirement as code (RAC) file;
- interpreting, by a requirement management interface, at least one test parameter from the RAC file;
- and
- evaluating the ML model based on the interpreted at least one test parameter from the RAC file.
Dependencies are inferred from the claim text.