TechNet is a very large technology semantic network. It currently consists of >4 million technology-related terms and semantic relations between them. The terms are retrieved from unstructured texts in over 6 million U.S. patents from 1974 to date and their pairwise semantic relations are calcualted using a neural network language model. TechNet outperforms Google Knowledge Graph, WordNet and ConceptNet for engineering text analysis and technical language processing. It can serve as an infrastructure to support a wide range of AI applications in the context of engineering and technology.
TechNet is generated and maintained by the researchers of Data-Driven Innovation Lab in SUTD-MIT International Design Center in Singapore University of Technology and Design.
For more information, please visit TechNet GitHub Repository and refer to our published article: (Sarica, S., Luo, J. and Wood, K.L., 2020. TechNet: Technology semantic network based on patent data. Expert Systems with Applications, 142, p.112995. 10.1016/j.eswa.2019.112995.)
Order: