Machine learning structured result generation

Abstract

Aspects of the present application relate to machine learning (ML) structured result generation. In an example, program code instructions that invoke an ML model indicate a result interface where model output is stored. The result interface is processed to generate a data format description of the result interface, such that input to the ML model further includes a data format description. As a result of providing the data format description as input to the ML model, the ML model is induced to generate a structured model output that corresponds to the result interface. The resulting model output is processed to generate an instance of the result interface, e.g., having one or more corresponding properties from the structured model output. Thus, the program code can ensure subsequent processing based on the generated instance of the result interface.

Images