Introduction

Patents, a form of intellectual property (IP), grant the inventor temporary rights to suppress competing use of an invention in exchange for a disclosure of the invention. It was once established to promote and/or control technical innovation and progress. The surge in global patent applications and the rapid technological progress pose formidable challenges to patent offices and related practitioners. For example, novelty is one of the essential requirements for patents, which takes a vast amount of resources and time for human assessment. Reviewing patents can take years because it is complex and detail-oriented. Even experienced examiners can overlook critical information or fail in judgment. In addition, drafting patent applications necessitates the expertise of qualified patent agents or attorneys. It requires a profound understanding of the invention's technical details and a familiarity with pertinent patent laws and language conventions. Meticulous and precise patent texts are essential for securing robust patent protection. However, drafting and revising patent applications are both time-intensive and financially demanding. Each round of revising can generate costs of up to thousands of dollars, presenting considerable challenges, particularly for small enterprises. These challenges overwhelm traditional manual methods of patent analysis and drafting. Consequently, there is a significant need for advanced computational techniques to automate patent-related tasks. Such automation not only enhances the efficiency of patent and IP management but also facilitates the development of technological innovation.

Researchers have investigated machine learning (ML) and natural language processing (NLP) methods for the patent field with highly technical and legal texts. In addition, the recent large language models (LLMs) have demonstrated outstanding capabilities across a wide range of general domain text-based tasks. These models are promising to become valuable tools in managing and drafting patent literature, the crucial documentation resource of technological advances. However, compared to the significant success of LLMs in the general domain, the application of LLMs in patent-related tasks remains under-explored due to their complexity. Therefore, we aim to apply cutting-edge LLMs to this specialized domain and exploit a so far underutilized highly-formalized technological knowledge source to boost and even automate innovation.

Related Publications

Natural Language Processing in Patents: A Survey, Lekang Jiang and Stephan Goetz.

Can Large Language Models Generate High-quality Patent Claims?, Lekang Jiang, Caiqi Zhang, Pascal A Scherz, Stephan Goetz. (Accepted to NAACL 2025)

Patent-CR: A Dataset for Patent Claim Revision, Lekang Jiang, Pascal A Scherz, Stephan Goetz. (Accepted to NAACL 2025)

I am a postdoctoral research associate supervised by Dr. Stephan Goetz in the Department of Engineering at the University of Cambridge. My research interests include magnetic field control and optimization, wireless power transfer, electric vehicle technologies, power electronics, biomedical engineering and neurosciences. Before this, I worked as a postdoctoral associate with the Department of Psychiatry & Behavioral Sciences, School of Medicine, Duke University. I received the Ph.D. degree in electrical and electronic engineering at the Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China, in 2022.

I am a PhD student supervised by Dr. Stephan Goetz in the Department of Engineering at the University of Cambridge. My research interests include computational neuroscience, modelling of transcranial magnetic stimulation, statistical models, biomedical engineering, control systems, and optimisation. I received a BEng degree in Electronic and Electrical Engineering from the University of Liverpool with the first class (Top One), and an MSc degree in Electrical Engineering Department from Imperial College London with distinction. I am currently studying and analysing neuromodulation variability involved in transcranial magnetic stimulation using mathematical techniques. Moreover, I am developing a new software for analysing the variability of motor-evoked potential as well. More information about my publication is available here. If you are interested in my project, please do not hesitate to contact me (km834@cam.ac.uk)!

I am a PhD student supervised by Dr. Stefan Goetz in the Department of Engineering at University of Cambridge. My research interests include power flow/quality control, grid-forming converters, and applications of WBG devices. You can find my publication here. I received the BEng degree in Electronic and Electrical Engineering from Southwest Jiaotong University, Chengdu, China, the BEng (first class) degree in Electrical and Electronic Engineering from the University of Leeds, Leeds, UK, both in 2021, and the MPhil degree in Engineering from the University of Cambridge, Cambridge, UK, in 2022. Aside from my academic pursuits, I am interested in football, gym activities, table tennis, and singing. More information about me is available here.

I am a PhD student in the Department of Engineering at the University of Cambridge, Wolfson College, supervised by Dr. Stephan Goetz. My research concerns mathematical and physical methods of modeling brain stimulation (Transcranial magnetic stimulation, TMS). Before this, I worked as a research assistant at Peking University (supervised by Dr. Guannan He). I obtained my master's degree in Applied Mathematics at the University of Cambridge (Part III) and a bachelor's degree in Applied Mathematics at The Chinese University of Hong Kong, Shenzhen.

I am a PhD student in the Department of Engineering at University of Cambridge, Churchill College, supervised by Dr.Stephan Goetz. My research is about the application of Natural Language Processing (NLP) and Large Language Models (LLMs) in the patent domain, including patent analysis and patent text generation. If you are interested in related topics, please feel free to contact me. Prior to this, I obtained my master degree in Advanced Computer Science at University of Cambridge and bachelor degree in Computer Science with Artificial Intelligence at the University of Nottingham. More information about me can be found at my personal website.

I am a PhD student in the Department of Engineering at the University of Cambridge, supervised by Dr. Stefan Goetz. My research focuses on medical imaging, computer vision, and augmented/virtual reality. I hold a BEng degree in Electronic and Electrical Engineering from University College London (2022) and an MSc degree in Artificial Intelligence from Imperial College London (2023). You can find more information about my publications here. If you are interested in my research or potential collaboration opportunities, please feel free to contact me (xh365@cam.ac.uk)!

I am previously a joint PhD in the Department of Engineering at the University of Cambridge. My research focuses on exploring integrated topologies, high-temperature module packaging, and the control strategy of resonant converters. Driven by a passion for innovation, I am committed to continuously enhancing my skills and knowledge. My ultimate goal is to contribute meaningfully to the field of power electronics and make a positive impact within the industry. I warmly invite you to engage in discussions and collaborations via mq234@cam.ac.uk if you share an interest in my research endeavors. Let's connect and explore new possibilities together!

Analysis of Circuits and Devices

Switch-mode Electronics

Switch-mode Electronics

Electricity and Environment

Electric Drive Systems

Integrated Digital Electronics

Electric Drive Systems

Integrated Digital Electronics

Electric Drive Systems

Integrated Digital Electronics