C3.ai, inc. (20250118099). DATA-EFFICIENT OBJECT DETECTION OF ENGINEERING SCHEMATIC SYMBOLS
DATA-EFFICIENT OBJECT DETECTION OF ENGINEERING SCHEMATIC SYMBOLS
Organization Name
Inventor(s)
Zhaoxi Zhang of Palo Alto CA US
Amir H. Delgoshaie of Redwood City CA US
Shouvik Mani of New York City NY US
DATA-EFFICIENT OBJECT DETECTION OF ENGINEERING SCHEMATIC SYMBOLS
This abstract first appeared for US patent application 20250118099 titled 'DATA-EFFICIENT OBJECT DETECTION OF ENGINEERING SCHEMATIC SYMBOLS
Original Abstract Submitted
a method includes obtaining an engineering schematic containing multiple symbols and connections involving the symbols, where different ones of the symbols in the engineering schematic represent different types of equipment. the method also includes identifying visual features of the engineering schematic. the method further includes processing the visual features using at least one trained machine learning model to (i) identify boundaries around the symbols in the engineering schematic and (ii) classify the symbols in the engineering schematic into multiple classifications, where different ones of the classifications are associated with different types of symbols.