A Method for Constructing a Digital Transformation Driving Mechanism Based on Semantic Understanding of Large Models

During the digital transformation process, enterprises encounter challenges such as insufficient semantic understanding of unstructured data and a lack of an intelligent decision-making basis in their operational mechanisms. This study proposes a method that combines a Large Language Model (LLM) with a knowledge graph. Firstly, a fine-tuned BERT (Bidirectional Encoder Representations from Transformers) model is utilized to perform entity recognition and relationship extraction on multi-source, heterogeneous texts. GPT-4 is then employed to generate semantically enhanced vector representations. Secondly, a two-layer graph neural network (GNN) architecture is designed to fuse the semantic vectors output by the LLM with business metadata, thereby building a dynamic and scalable enterprise knowledge graph. Then, reinforcement learning is introduced to optimize decision path generation, and a reward function drives the iteration mechanism. In the case of the manufacturing industry, this mechanism reduces the response time of the equipment failure scenario from 7.8 hours to 3.7 hours, and the F1 value reaches $94.3 \%$. This method significantly enhances the intelligence level and execution efficiency of the digital transformation driving mechanism by integrating large model semantic understanding with structured knowledge.