Background

Universities, as centers of innovation and research, generate vast amounts of knowledge and research activities across diverse fields. From publications and patents to collaborative projects and spin-offs, academic institutions produce a continuous stream of intellectual output that represents significant innovation potential. However, this wealth of research activities creates substantial challenges in managing, analyzing, and extracting valuable insights from the accumulated intellectual capital.

Recent advances in Large Language Models (LLMs) have opened new possibilities for automatically processing and understanding complex academic content at scale. Unlike traditional text analysis methods, LLMs can comprehend nuanced research contexts, identify interdisciplinary connections, and extract meaningful patterns from heterogeneous data sources. While AI systems such as ChatGPT, Claude or Gemini are being used increasingly in everyday applications, their potential for systematic analysis of university innovation ecosystems remains largely untapped.

Traditional approaches to analyzing university innovation activities often rely on manual processes and limited metrics, making it difficult to capture the full scope of research capabilities and emerging innovation patterns. Recent developments in Large Language Models (LLMs) and data inclusion technologies offer promising opportunities to automatically analyze, categorize, and extract meaningful insights from university research data, publications, and innovation activities.

While LLMs have shown remarkable capabilities in understanding and processing complex academic content, their application to comprehensive innovation management within university ecosystems remains underexplored. The challenge lies in developing systematic approaches that can process heterogeneous data sources, identify innovation patterns, and generate customized reports that support strategic decision-making in academic institutions.

Research Goal

The aim of this research is to investigate how AI can be leveraged to analyze innovation and research activities within universities and generate customized reports for different stakeholders. The research should explore the integration of LLMs with Knowledge Graph technologies to create a comprehensive system for managing innovation and capability knowledge.

As a starting point, suitable data sources and metrics for measuring university innovation activities should be identified from current literature and practice. Based on these findings, different AI-powered methods should be implemented to automatically analyze research outputs, identify innovation patterns, and extract capability knowledge. The system should be capable of generating tailored reports for various audiences, such as university management, research groups, or external partners.

To evaluate the effectiveness of the developed approaches, the AI-generated analyses and reports should be compared with traditional manual evaluation methods through expert interviews or case studies with university stakeholders.

Your Profile

• You are interested in the field of gen-AI
• You have experience with python and common frameworks for AI
• Experience with LLMs and optionally Knowledge Graphs
• You are highly motivated to work on recent real-world problems in a self-organized and goal-oriented working mode, and you bring in your own ideas
• Very good English skills as the thesis will be written in English

Details

• Start: Immediately
• Language: English

We offer you an exciting research topic, close supervision, and the opportunity to develop practical as well as theoretical skills. If you are interested, please send a current transcript of records, a short CV, and a brief motivation (2-3 sentences) to Jonas Liebschner jonas.liebschner∂kit.edu