Research on Knowledge-enhanced Large Model Generation Framework Technology for Business-oriented Requirements
In recent years,large language model technology has been flourishing and has made significant progress in general fields.However,the lack of training data in key areas such as military and government affairs has made it difficult for large models in specialized domains to meet user needs,particularly in terms of multi-type data retrieval tasks for business requirements,where general large models face bottlenecks.This paper proposes a knowledge-enhanced large model cross-data retrieval framework and designs an evolution mechanism for the retrieval capabilities of large models that integrate and grow knowledge.By utilizing the self-supervised signals of large language models to drive the continuous generation of domain knowledge and leveraging accumulated knowledge to continuously enhance the retrieval capabilities of large models,we conduct prototype system construction and experimental validation in typical business scenarios.The framework's ability to handle user business information queries and result generation is tested in these scenarios.Experimental results show that high-quality knowledge helps to improve the precision and effectiveness of the results generated by large models.
large language modelknowledge enhancementcross data retrieval
NETL
NSTL
万方数据
