---
title: "Graphical Deep Knowledge for Intelligent Machine Drafting"
authors:
  - "James Geller"
  - "Stuart C. Shapiro"
doi: ""
url: "https://ijcai.org/proceedings/1987/109"
pdf: "https://ijcai.org/proceedings/1987/0109.pdf"
venue: "Proceedings of the Tenth International Joint Conference on Artificial Intelligence"
year: 1987
pages: "545-550"
track: "Knowledge Representation"
keywords:
---

# Graphical Deep Knowledge for Intelligent Machine Drafting

James Geller, Stuart C. Shapiro

*Proceedings of the Tenth International Joint Conference on Artificial Intelligence*, pages 545-550.

## Abstract

T he problem of Intelligent Machine Drafting is presented, a nd a de sc ription of an ex is ting implementation as part of a graphical generator functi on is given. The concept of Graphical Deep Knowledge is defined as a representational basis for Intelligent Machine Drafting problems as well as for physical object displays. A (partial) task domain analysis for Graphical Deep Knowledge is presented. Primitives that are necessary to deal with a world of 2-D forms and colors are introduced. Among them a re primitives for describing forms, positions, parts, attributes, sub-assemblies, and an abstraction hierarchy. The use of the "linearity principle" for knowledge structure derivation fr om natural language utterances is shown.