Toshiba AI Technology Catalog

  • Placement and Design
  • Knowledge organization

Extraction of knowledge graphs

Illustrate connections in functions from specifications related to the product family.


  • Extract common functions from text in system specifications by analysis of their relationships with domain knowledge.
  • Apply this technology to modular design particularly in derivative system development.

Applications



  • Design and development of increasingly diverse indent products; e.g., through derivative development
  • Standardization for modularizing product families
  • Inventory functions extracted from system specifications and other sources

Benchmarks, strengths, and track record



  • Semi-automated method in iterative learning way enables to achieve enough quality of the common functional structure in a short period.

Inquiries



Please include the title “Toshiba AI Technology Catalog: Extraction of knowledge graphs” or the URL in the inquiry text.
Please note that because this technology is currently the subject of R&D activities, immediate responses to inquiries may not be possible.

References:

  • Eiichi Sunagawa et.al.; “An Approach to Extract Functional Model in System Design Documents”; Japanese Society for Artificial Intelligence (JSAI) 44th SWO Special Interest Group, 2018.
  • E. Sunagawa, et al., “Extraction of Functional Structure Graph from System Design Documents,” JIST2018.