Electronic Arts Inc.
MACHINE-LEARNING ASSISTED AUTOCOMPLETE IN VISUAL PROGRAMMING

Abstract:

A visual-programming tool accesses a datastore of existing program data, which includes program code associated with a plurality of programs, (e.g., games), stored as multi-layer trees of nodes with logical connections signifying relationships between nodes of adjacent layers. The tool uses machine learning to determine multi-layer trees of predictions including at least one chain of nodes from the multi-layer tree of nodes. The tool provides one or more of the multi-layer trees of predictions including chains of nodes for presentation via a graphical-user interface and receives a gliding gesture input indicating a decision between nodes of the one or more layers. The input indicates a decision associated with selecting a chain of nodes when the input traverses more than one layer. The visual-programming tool provides further layers from the one or more multi-layer trees of predictions based on the received input without requiring acceptance of individual nodes at each layer.