Skip to content
Go back

[Submitted] Mapping Technological Convergence via LLM-enhanced Analytics

Published:  at  09:00 AM
... views

🏆 Research Status & Connection

This research is currently under review in a top-tier SCIE-indexed journal. It is a significantly expanded and refined version of the methodology that was recognized for its innovation at a recent academic conference.


📌 Research Overview

To engineer the future of markets, we must first understand the historical trajectory of technological supply. This research introduces a novel methodology—Semantic Main Path Analysis (SMPA)—to accurately trace the evolutionary path of emerging technologies while overcoming the “citation inertia” inherent in traditional models.

⚙️ Methodology

The framework bridges complex network analysis with modern Natural Language Processing (NLP):

  1. Semantic Similarity Integration: Utilizes Large Language Model (LLM)-based sentence embeddings to calculate the contextual similarity between patents, moving beyond purely quantitative citation counts.
  2. Knowledge Mapping: Extracts the Semantic Main Path by applying network algorithms on top of these semantic weights, identifying the true backbone of technological innovation.

For the foundational model and initial award details, please refer to the Conference & Award Archive.


Share this research on:

Previous Research
Chatbot Design for Structuring User Input Data via LLM (Poster Award)
Next Research
TRIZ & Graph RAG-based Intelligent Patent Convergence (IPC) Service (Creative Award)