US Patent 11625141 User interface generation with machine learning

A system includes a processor configured to perform operations, including receiving, from a client device, a request, associated with a user identifier, for rendering of a graphical user interface (GUI), and obtaining, based on the request and from persistent storage, a framework definition that specifies a first plurality of components and a layout thereof within the GUI. The operations also include determining a second plurality of components by way of a machine learning model and based on attributes associated with the user identifier, and determining, for each respective component of the second plurality of components, a corresponding visual format and a corresponding position within the GUI. The operations further include updating the framework definition by combining the first plurality of components and the second plurality of components based on the corresponding visual format and the corresponding position, and transmitting the framework definition as updated to the client device.