Case-based Reasoning for Knowledge Capitalization in Inventive Design Using Latent Semantic Analysis

Abstract

Nowadays, innovation represents one of the most crucial factors driving the success of companies. The Theory of Inventive Problem Solving (also known as TRIZ) is a well-established method to facilitate systematic inventive design. Although, TRIZ allows solving inventive problems through a panoply of knowledge sources, it may make inventive problem solving a time-consuming, experience demanding process and lead to waste of resources of the companies. To avoid the use of these tools and to help new users in solving their inventive problems without completely mastering TRIZ, we propose in this paper an approach based on the use of the Case-based reasoning (CBR) in order to capitalize experience. CBR is a knowledge paradigm that solves a new problem by finding the old similar cases and reusing them. The retrieval is conducted in order to find the old similar cases, and the old solutions of the retrieved cases are adapted to solve the new problem. In this paper, a systematic three-level adaptation is proposed to reduce the effort required of the users in choosing the suitable solution to solve their problem. An example is used to illustrate in detail the proposed approach.

BibTeX

@inproceedings{zhang:hal-02047114,
  TITLE = {{Case-based Reasoning for Knowledge Capitalization in Inventive Design Using Latent Semantic Analysis}},
  AUTHOR = {Zhang, Pei and Essaid, Amira and Zanni-Merk, Cecilia and Cavallucci, Denis},
  URL = {https://hal.science/hal-02047114},
  BOOKTITLE = {{Procedia Computer Science}},
  ADDRESS = {Marseille, France},
  PUBLISHER = {{Elsevier}},
  VOLUME = {112},
  PAGES = {323-332},
  YEAR = {2017},
  MONTH = Sep,
  DOI = {10.1016/j.procs.2017.08.004},
  KEYWORDS = {Latent Semantic Analysis ; Inventive Design Theory ; TRIZ ; Case-based Reasoning ; Experience Reuse},
  PDF = {https://hal.science/hal-02047114v1/file/islandora_71148.pdf},
  HAL_ID = {hal-02047114},
  HAL_VERSION = {v1},
}