The application discloses a
large model and
knowledge graph enabled intention driving network design method, comprising the following steps: S101, a user inputs a user intention through a front-end
natural language interaction interface, and performs a pretreatment operation on the user intention; S102, a pretreated user intention is classified based on a few-shot learning method, and a
large model cooperation method extracts key information of the user intention and constructs an intention
knowledge graph based on the key information; S103, a network state
knowledge graph is constructed; S104, an application program interface provided by an underlying layer is called by using intention understanding and reasoning capability of the
large model, so that mapping of the user intention to an underlying
network strategy and issuing are realized; and S105, the large model performs dynamic real-time adjustment based on network state knowledge graph information. The application realizes intention
semantic mining,
adaptation of intention demand and underlying resource capability, so as to bridge a
semantic gap between the user intention, strategy management and the underlying network, and improve network operation efficiency.