DiTTO-LLM: Framework for Discovering Topic-based Technology Opportunities via Large Language Model

2025-09-10

AI Summary

This study addresses the challenge of identifying emerging technological opportunities. Methodologically, it proposes a patent analysis framework that integrates large language models (LLMs) with time-aware topic modeling: LLMs are employed to extract fine-grained technical themes from patent texts and model their semantic evolution, while temporal dependency mining uncovers dynamic inter-technical relationships; conversational prompt engineering further enhances interpretability in detecting nascent directions. The key contribution lies in the first deep coupling of LLMs’ thematic understanding capability with temporal topic modeling, enabling traceable, fine-grained dynamic modeling of technological evolution. Experiments on an AI-domain patent dataset demonstrate the framework’s efficacy in identifying paradigm shifts—such as the transition toward “daily accessibility”—and its strong capability in trend forecasting and opportunity early warning.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Technology opportunities are critical information that serve as a foundation for advancements in technology, industry, and innovation. This paper proposes a framework based on the temporal relationships between technologies to identify emerging technology opportunities. The proposed framework begins by extracting text from a patent dataset, followed by mapping text-based topics to discover inter-technology relationships. Technology opportunities are then identified by tracking changes in these topics over time. To enhance efficiency, the framework leverages a large language model to extract topics and employs a prompt for a chat-based language model to support the discovery of technology opportunities. The framework was evaluated using an artificial intelligence patent dataset provided by the United States Patent and Trademark Office. The experimental results suggest that artificial intelligence technology is evolving into forms that facilitate everyday accessibility. This approach demonstrates the potential of the proposed framework to identify future technology opportunities.

Problem

• Identifies emerging technology opportunities using temporal relationships
• Leverages large language models to extract topics from patents
• Tracks topic changes over time to discover technology evolution

Innovation

• Leverages large language model for topic extraction
• Uses prompt-based chat model for opportunity discovery
• Tracks temporal topic changes in patent datasets