In modern industrial environments, there may be numerous independent applications deployed throughout a facility, all performing different tasks, gathering different data, and communicating data and control information among one another. For example, this may include industrial control, quality control, work instructions, training, oversight, and so forth. Against this backdrop, an AI system is trained with a large language model to assist in characterization of new applications, in order to support administration and management of the software infrastructure for a facility.

A video of a manufacturing process, along with accompanying narration and other descriptive materials, can be used to automatically generate an application for control of the manufacturing process, or assist in a semi-automated generation of the application. As a significant advantage, a generative artificial intelligence system can support the application creation process by providing domain-specific process knowledge and no-code/low-code programming tools to convert general process descriptions into an application that is executable in the manufacturing environment for the process.

In an industrial processes, a properly instrumented line facilitates capture of data including detected steps, application input, and execution graph transitions, that permit the creation of empirical models of process timing. In this context, a process controlled by individual applications, e.g., at manufacturing workstations, provides a proxy for overall process timing by dividing a workflow into a number of discrete steps completed at each workstation, and further into any number of sub-steps, each controlled by a user and explicitly completed, e.g., by user interactions with widgets or other controls of the application. These applications provide a useful framework for modeling execution timing by providing an initial, implicit model for workflow (based on application control logic) that also facilitates automated detection of process sub-steps based on execution flow, as well as detection and measurement of the contributions of individual widgets and/or combinations of widgets to the process timing. By gathering data in this manner, mixed statistical distributions can be applied based on individual timing data for each possible sub-step, widget, process step, and the like performed with each application.

Data from manufacturing is highly uncontextualized and siloed, requiring expert knowledge of context and substantial data pre-processing to support meaningful queries and visualizations. To address this problem, data for a number of sources in a manufacturing context can be retrieved and converted into an intermediate representation in a natural language or near-natural language form, which can in turn be ingested by a generative AI engine, along with suitable prompts by the user to summarize, analyze, and make recommendations based on the data.