Latent semantic extraction and analysis for TRIZ-based inventive design

Résumé

During the development of TRIZ, several knowledge sources have been developed to solve inventive problems. Even though they are about close notions, the level of detail of the descriptions is very dissimilar, making it difficult for the user to operate with them in a systematic way. To cope with this difficulty, we are interested in finding semantic links among these sources, with the goal of assisting the inventive design expert during his activities. Taking into account that all the TRIZ knowledge sources are represented as short texts and directly applying conventional topic models on such short texts may not work well, an extended latent semantic analysis model is proposed to find the missing links among the TRIZ knowledge sources. With the help of these obtained links, several heuristic abstract solutions can be obtained. In order to show this whole process, the resolution of the case of the 'Auguste Piccard's Stratostat' is elaborated in detail.

BibTeX

@article{yan:hal-02047109,
  TITLE = {{Latent semantic extraction and analysis for TRIZ-based inventive design}},
  AUTHOR = {Yan, Wei and Liu, Hong and Liu, Yusheng and Wang, Jihua and Zanni-Merk, Cecilia and Cavallucci, Denis and Yan, Xiaodan and Zhang, Liang},
  URL = {https://hal.science/hal-02047109},
  JOURNAL = {{European Journal of Industrial Engineering}},
  VOLUME = {12},
  NUMBER = {5},
  PAGES = {661--681},
  YEAR = {2018},
  DOI = {10.1504/EJIE.2018.094593},
  KEYWORDS = {TISM ; term-item semantic matrix ; semantic weight ; LSA ; latent semantic analysis ; knowledge sources ; TRIZ ; theory of inventive problem solving},
  HAL_ID = {hal-02047109},
  HAL_VERSION = {v1},
}