Generative Design Ideation: A Natural Language Generation Approach

@article{Zhu2022GenerativeDI,
  title={Generative Design Ideation: A Natural Language Generation Approach},
  author={Qihao Zhu and Jianxi Luo},
  journal={ArXiv},
  year={2022},
  volume={abs/2204.09658}
}
This paper aims to explore a generative approach for knowledge-based design ideation by applying the latest pre-trained language models in artificial intelligence (AI). Specifically, a method of fine-tuning the generative pre-trained transformer using the USPTO patent database is proposed. The AI-generated ideas are not only in concise and understandable language but also able to synthesize the target design with external knowledge sources with controllable knowledge distance. The method is… 
[PDF] Semantic Reader
6 Citations
Background Citations
2
Methods Citations
3

Figures and Tables from this paper

6 Citations

Biologically Inspired Design Concept Generation Using Generative Pre-Trained Transformers

Biological systems in nature have evolved for millions of years to adapt and survive the environment. Many features they developed can be inspirational and beneficial for solving technical problems…

ChatGPT and Other Large Language Models as Evolutionary Engines for Online Interactive Collaborative Game Design

This paper presents a collaborative game design framework that combines interactive evolution and large language models to simulate the typical human design process and uses users' feedback for selecting the most promising ideas.

Natural language processing in-and-for design research

Abstract We review the scholarly contributions that utilise natural language processing (NLP) techniques to support the design process. Using a heuristic approach, we gathered 223 articles that are…

Enhancing patent retrieval using text and knowledge graph embeddings: a technical note

The proposed patent retrieval method is applied to a set of patents corresponding to a product family and an inventor's portfolio and identifies using a classification task that the concatenation of text, citation, and inventor embeddings offers a plausible representation of a patent.

Innovation Slowdown: Decelerating Concept Creation and Declining Originality in New Technological Concepts

The creation of new technological concepts through design reuses, recombination, and synthesis of prior concepts to create new ones may lead to exponential growth of the concept space over time.…

Patent Data for Engineering Design: A Critical Review and Future Directions

This review surveys the patent-for-design literature categorized by their contributions to design research and practice, including design theories, methods, tools, and strategies, as well as the forms of patent data and the data science methods in respective studies.

15 References

Idea generation with Technology Semantic Network

A new methodology of using the Technology Semantic Network (TechNet) to stimulate idea generation in engineering design to guide the inference of new technical concepts in the white space surrounding a focal design domain according to their semantic distance in the large TechNet.

A Study of Pre-trained Language Models in Natural Language Processing

It is expected this article will provide a practical guide for learners to understanding, using and developing PLMs with the abundant literature existing for various NLP tasks.

Computer-Aided Design Ideation Using InnoGPS

This paper demonstrates the procedures of using InnoGPS as a data-driven rapid ideation tool to generate new rolling toy design concepts and fuse design science, network science, data science and interactive visualization to make the design ideation process data- driven, theoretically-grounded, visually-inspiring, and rapid.

Guiding data-driven design ideation by knowledge distance

Language Models are Unsupervised Multitask Learners

It is demonstrated that language models begin to learn these tasks without any explicit supervision when trained on a new dataset of millions of webpages called WebText, suggesting a promising path towards building language processing systems which learn to perform tasks from their naturally occurring demonstrations.

Language Models are Few-Shot Learners

GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic.

Deep Generative Models in Engineering Design: A Review

A review and analysis of Deep Generative Learning models in engineering design and key challenges and limitations currently seen in DGMs across design fields, such as design creativity, handling constraints and objectives, and modeling both form and functional performance simultaneously are identified.

Computer-Based Design Synthesis Research: An Overview

Advances in function-based, grammar- based, and analogy-based synthesis approaches and their contributions to computational design synthesis research in the last decade are reviewed.

From Brainstorming to C-Sketch to Principles of Historical Innovators: Ideation Techniques to Enhance Student Creativity.

heart and soul of engineering is innovation and our ability to improve the human condition through design. To enrich engineering education, it is critical that we advance our teaching in innovation…

Self-Supervised Contextual Keyword and Keyphrase Retrieval with Self-Labelling

This paper proposes to use contextual features from bidirectional transformers to automatically label short-sentence corpus with keywords and keyphrases to build the ground truth and avoids the human time to label the keywords and do not need any prior knowledge.