US 2023/0419168 A1 · OBTAINING USER FEEDBACK ON MODELS VIA A HUMAN MACHINE INTERFACE (HMI)

Abstract

Various embodiments of the present technology generally relate to industrial automation environments. More specifically, embodiments include systems and methods to train machine learning systems based on user operations in an industrial automation environment. In some examples, a Human Machine Interface (HMI) component displays a machine learning output indicating a training state of a machine learning model on a user interface and user feedback regarding the training state. A machine learning interface component weights feature vectors based on the user feedback and supplies the weighted feature vectors to the machine learning model. The machine learning interface component receives another machine learning output that indicates an updated training state for the model. The HMI component displays the output indicating the updated training state of the model, receives additional user feedback regarding the updating training state, and transfers the additional user feedback to the machine learning interface component.

Claims20

Dependent claims

A system to train machine learning systems based on user operations in an industrial automation environment, the system comprising:

a memory that stores executable components;
and
a processor, operatively coupled to the memory, that executes the executable components, the executable components comprising:
a Human Machine Interface (HMI) component configured to display a first machine learning output indicating a training state of a machine learning model on a user interface, receive a user input comprising user feedback regarding the training state, and transfer the user feedback to a machine learning interface component;
the machine learning interface component configured to receive the user feedback, weight feature vectors configured for ingestion by the machine learning model based on the user feedback, and supply the weighted feature vectors to the machine learning model;
the machine learning interface component configured to receive a second machine learning output from the machine learning model wherein the second machine learning output indicates an updated training state for the machine learning model, and transfer the second machine learning output to the HMI component;
and
the HMI component configured to display the second machine learning output indicating the updated training state of the machine learning model, receive an additional user input comprising additional user feedback regarding the updating training state, and transfer the additional user feedback to the machine learning interface component.

5 more elements

A method for training machine learning systems based on user operations in an industrial automation environment, the method comprising:

displaying, by a system comprising a processor, a first machine learning output indicating a training state of a machine learning model on a user interface and receiving a user input comprising user feedback regarding the training state;
weighting, by the system, feature vectors configured for ingestion by the machine learning model based on the user feedback and supplying the weighted feature vectors to the machine learning model;
receiving, by the system, a second machine learning output from the machine learning model wherein the second machine learning output indicates an updated training state for the machine learning model;
and
displaying, by the system, the second machine learning output indicating the updated training state of the machine learning model and receiving an additional user input comprising additional user feedback regarding the updating training state.

2 more elements

A non-transitory computer-readable medium stored thereon instructions to train machine learning systems based on user operations in an industrial automation environment that, in response to execution, cause a system comprising a processor to perform operations, the operations comprising:

displaying a first machine learning output indicating a training state of a machine learning model on a user interface and receiving a user input comprising user feedback regarding the training state;
weighting feature vectors configured for ingestion by the machine learning model based on the user feedback and supplying the weighted feature vectors to the machine learning model;
receiving a second machine learning output from the machine learning model wherein the second machine learning output indicates an updated training state for the machine learning model;
and
displaying the second machine learning output indicating the updated training state of the machine learning model and receiving an additional user input comprising additional user feedback regarding the updating training state.

2 more elements

Dependencies are inferred from the claim text.

Obtaining user feedback on models via a human machine interface (hmi)

Life of this patent

Obtaining user feedback on models via a human machine interface (hmi)

Life of this patent

Abstract

Claims20