I have a decade of experience as a software engineer in the tech industry, working on projects for both startups and large companies. My interest in machine learning began when I explored tools for controlling computers through voice commands and audio interaction, long before the ChatGPT era. This fascination motivated me to pursue a master’s in data science, where my thesis focused on leveraging Generative AI to create synthetic data for privacy protection concerns. This experience further inspired me to investigate how generative AI can be applied in intellectual property processes and services, which are inherently privacy-focused during the prosecution phase.
Research
In today's rapidly evolving technological landscape, drafting patent applications has become an increasingly complex task. Patent attorneys, who are responsible for translating innovative ideas into legally sound documents, face significant challenges in ensuring that patents are thorough, accurate, and legally robust. This is where AI-powered patent drafting can make a real difference.
This project seeks to revolutionize the patent drafting process by developing a suite of generative AI tools aimed at streamlining and enhancing the work of patent professionals. By leveraging large language models, the project provides an effective solution for automating key aspects of the drafting process, such as generating patent specifications, refining technical descriptions, and suggesting language that meets legal standards.
What sets this project apart is its emphasis on data security. Given that patent applications often involve highly sensitive intellectual property, protecting this information is of utmost importance. To address these concerns, the project integrates a secure, on-premise solution, ensuring that all data remains within the client's network, minimizing the risk of external breaches. This approach allows patent attorneys to take full advantage of AI while maintaining complete control over the confidentiality of their clients' innovations.
By incorporating AI into patent law practices, this project not only aims to save time and reduce human error, but also has the potential to drive innovation in the patent field. Offering a reliable and secure AI solution, it enables patent attorneys to focus more on the creative and strategic aspects of their work, ultimately reshaping the way intellectual property is protected and represented.
My research groups
-
Data Intensive Software Technologies and Applications (DISTA) The research group Data Intensive Software Technologies and Applications studies data-driven approaches, such as machine learning,…
-
Linnaeus University Centre for Data Intensive Sciences and Applications The DISA research centre at Linnaeus University focuses its efforts on open questions in collection, analysis and utilization of…
My ongoing research projects
Publications
Conference paper (Refereed)
- Mawaldi, M.H., Kastrati, Z., Gustafsson, A. (2025). AWACopilot : A Secure On-Premise Large Language Model-Based Solution for Enhanced Patent Drafting. PatentSemTech 2025: Patent Text Mining and Semantic Technologies 2025.