Computer-aided classification of patents oriented to TRIZ

Abstract

TRIZ has been widely acknowledged as an effective tool to solve technical problems. In TRIZ theory, a significant operation of product innovation is to solve design contradictions. When an engineer formulates his problem as a contradiction, the contradiction matrix helps him to identify a representative contradiction and inventive principles. But inventive principles are abstract, it will be more helpful to generate innovative problem-solving ideas for innovators if they obtain related examples from published patents which have used the same inventive principles in different fields. Most of the current available automatic patent classification systems are based on technology field such as IPC and they are not suitable for TRIZ. Recent advance of computational linguistics allowed us to integrate text mining and TRIZ for patent classification. In this paper, a computer-aided approach to classify patents according to inventive principles is proposed.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 14 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.