TechNet, namely Technology Semantic Network, 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. They represent These terms represent technical concepts regarding functions, components, configurations or working mechanisms. Their pairwise semantic relations are calculated using a neural network language model and indicate the technical relevance between the technical concepts. 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.
For more information, please refer to the following publication: 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.
TechNet created and maintained by Data-Driven Innovation Lab in SUTD-MIT International Design Center in Singapore University of Technology and Design.