Systems and methods for generating a gui for processing by a generative machine learning model
AssigneeShopify Inc.
InventorAtes Göral
Life of this patent
Estimating the term…
Loading patent…
AssigneeShopify Inc.
InventorAtes Göral
Estimating the term…
Frames depicting a graphical user interface (GUI), e.g. that may be presented to a user, may not be well suited for processing by a multimodal generative machine learning (ML) model. For example, frames may undergo some distortion in order to be resized to dimensions that are suitable for inference by the generative ML model. As such the image may be scaled down and certain GUI elements may be missing, distorted or otherwise skewed. Additionally, the frames may include particular fonts and/or colours, etc. that are difficult from an image processing perspective to be clearly read/interpreted by the generative ML model. To address this problem, computer-executable code defining model-specific styling can be obtained and applied to a set of GUI elements. Then, when the set of GUI elements is rendered, the resulting GUI may be better suited for use in prompting the generative ML model.
A computer-implemented method comprising:
A non-transitory computer-readable medium having stored thereon computer-executable instructions that, when executed by a computer, cause the computer to perform operations comprising:
A system comprising:
Dependencies are inferred from the claim text.