Towards Populating Generalizable Engineering Design Knowledge
share
Aiming to populate generalizable engineering design knowledge, we propose a method to extract facts of the form <head entity, relationship, tail entity> from sentences found in patent documents. These facts could be combined within and across patent documents to form knowledge graphs that serve as schemes for representing as well as storing design knowledge. Existing methods in engineering design literature often utilise a set of predefined relationships to populate triples that are statistical approximations rather than facts. In our method, we train a tagger to identify both entities and relationships from a sentence. Given a pair of entities, we train another tagger to identify the specific relationship tokens. For training these taggers, we manually construct a dataset of 44,227 sentences and corresponding facts. We benchmark our method against two typically recommended approaches. We apply our method by extracting facts from sentences found in patents related to fan systems. We build a knowledge base using these facts to demonstrate how domain ontologies could be constructed and contextualised knowledge of subsystems could be visualised. We then search the knowledge base for key issues prevailing in fan systems. We organize the responses into knowledge graphs and hold a comparative discussion against the opinions about the key issues from ChatGPT.
READ FULL TEXT