Abstract Design and innovation processes primarily synthesize the knowledge of existing technological artifacts. Understanding the foundations of such artifact-level knowledge is essential for enabling the knowledge retrieval and representation that govern these syntheses. In this study, we analyze a large, stratified sample of 33,881 patent descriptions across the total technology space. We populate knowledge graphs of these descriptions by combining factual triplets (entity:: relationship:: entity) extracted at the sentence level. From these knowledge graphs, we uncover the linguistic and structural foundations of the knowledge of technological artifacts. Linguistically, we identify syntactic patterns that explain how entities and relationships are constructed at the term level. Structurally, we identify motifs, including dominant 3-node and 4-node subgraph patterns, that reveal how entities and relationships are combined locally in artifact descriptions. Delving into these motifs reveals that natural language artifact descriptions primarily capture the design hierarchy of artifacts. At a local level within artifact descriptions, the motif analyses reveal that only abstract technical knowledge is captured, indicating potential limitations of relying on text-mining for knowledge-intensive tasks. Based on these observations, we propose and demonstrate knowledge specification strategies that can help simplify and modularize knowledge structures populated from technological artifact descriptions.
Siddharth et al. (Thu,) studied this question.