This Patent Knowledge Design Tool assists designers, engineers and Research & Development managers ("designers") in the innovation process. It provides quick insight into the motivations and key design parameters of existing designs, plus an automatic diagram of their working principles, from a search of existing mechanical design patents.
Designers, especially in SMEs, need to improve their awareness of relevant Intellectual Property (IP) in order to avoid potential patent infringement and also identify areas of innovation opportunity. Existing patent search and retrieval tools are mainly used by larger companies and their IP experts.
In order to identify relevant prior art using a conventional patent retrieval system; the designer will typically need to enter appropriate keywords, where semantics has a considerable effect on the results obtained.
For designers this process is too time-consuming and they would benefit from output that delivers concise technical insight into the working principle, motivation and other design-related information not produced by existing tools.
The tool automatically extracts knowledge that is contained in key sections of patents using Natural Language Programming (NLP) that applies sentiment analysis to the background and description sections of the patent that uniquely identify ‘motivation’ text identified by its negative sentiment.
The working principle is extracted from the abstract section also using NLP but relying on Subject-Action-Object (SAO) triplet format found in the text. This knowledge is then automatically transformed into Design Requirements (DR), Functional Attributes (FA) and a design structure visualisation based on a Function Analysis Diagram variant developed by this team, for use by the designers in their design process.
Currently, this output is presented in patent terms and the aim is to continue developing these to become expressed as general terms. Automatic refers to the use of Python routines to enable the automated patent data extraction from patents on-line and/or in a database. It also refers to the use of NLP.
- Broaden IP awareness and design knowledge of designers.
- Stimulate novel designs and innovation.
- Reveal opportunities for securing IP and avoid conflict.
- Improve knowledge sustainability.
- Sorce, S., Malizia, A., Gentile, A., Jiang, P., Atherton, M., Harrison, D., Evaluation of a Visual Tool for Early Patent Infringement Detection During Design, 7th International Symposium on End-User Development (IS-EUD 2019), Hertfordshire, 10-12 July, 2019.
- Jiang, P., Atherton, M., Sorce, S., Harrison, D., Malizia, A., Design for invention: a framework for identifying emerging design–prior art conflict, Journal of Engineering Design, Vol 29(10), Taylor & Francis, online 12 September 2018: 596-615. ISSN: 0954-4828 (print) ISSN: 1466-1837 (on-line). doi: 10.1080/09544828.2018.1520204.
- Atherton, M., Jiang, P., Harrison, D., Malizia, A., Design for invention: annotation of Functional Geometry Interaction for representing novel working principles, Research in Engineering Design, Vol 29(2), Springer, April 2018, 245-262. (published on-line September 2017 ISSN: 1435-6066 (online)). doi: 10.1007/s00163-017-0267-2.
- Sorce, S., Malizia, A., Jiang, P., Atherton, M., Harrison, D., A Novel Visual Interface to Foster Innovation in Mechanical Engineering and Protect from Patent Infringement, 2nd International Conference on Graphics, Images and Interactive Techniques (CGIIT), Hong Kong, China, 23-25 February, 2018. In Journal of Physics: Conference Series (Vol. 1004, No. 1, p. 012024). IOP Publishing. doi :10.1088/1742-6596/1004/1/012024.
- Jiang, Pingfei, Atherton, Mark, Harrison, David, Malizia, Alessio, Framework of mechanical design knowledge representations for avoiding patent infringement, International Conference on Engineering Design, 2017, pp 81-90, Vancouver, Canada, 21-25 August, 2017. In DS 87-6 Proceedings of the 21st International Conference on Engineering Design (ICED 17) Vol 6: Design Information and Knowledge, Vancouver, Canada, 21-25.08. 2017 (pp. 081-090).
Meet the Principal Investigator(s) for the project
Professor Mark Atherton -
Mark is a Professor in the Department of Mechanical and Aerospace Engineering. He is a Chartered Engineer and Fellow of the Institution of Mechanical Engineers. He has developed industrial products and manufacturing systems, and is currently working with industrial organisations on dental drill noise reduction (Dental drill noise reduction device), robotic servicing of trains (Lab-based prototype for automated train fluid servicing) and design tools for invention (On-line tool to intelligently interpret design information contained in patents). Mark teaches engineering design and design optimisation.
BSc(Hons) in Mechanical Engineering from Aston University, Birmingham.
MSc/DIC in Industrial Robotics and Manufacturing Automation from Imperial College, London.
PhD in Mechanical Engineering Design from City University, London.
Industrial experience: apprenticeship with Rubery Owen, followed by engineering positions with Driver Southall (GEC), Otis Elevator, and Redland Engineering.
Academic posts at London South Bank University and Brunel University London, plus visiting professor at Tokyo Univeristy of Science and Univeristy of Modena.
Chartered Engineer, Fellow of the Institution of Mechanical Engineers.
Project last modified 18/06/2021