Design of RAG Enterprise Architecture Knowledge Retrieval Service Based on Improved Generative Adversarial Network
Abstract
With the continuous improvement of artificial intelligence development level, enterprise architecture, as a systematic management framework, is increasingly valued by enterprises. Knowledge management and retrieval services in enterprise architecture are of great significance for improving operational efficiency and innovation capabilities of enterprises. To improve the accuracy and efficiency of enterprise architecture knowledge retrieval, research is conducted on designing enterprise architecture knowledge retrieval services based on RAG architecture, and using generative adversarial networks to increase adversarial training in the generation and retrieval process, thereby optimizing the coordination of retrieval and generation, and improving the accuracy and credibility of generated content. And based on it, use attention mechanism to improve and enhance retrieval accuracy. The outcomes denoted that the accuracy of the research method was as high as 91.42% and 92.06% in different datasets. The AUC reached 0.894 and 0.903 respectively. The shortest average response time and computation time for the research method are 2.51 seconds and 20.06 seconds, respectively. In datasets with larger data volumes, the longest average response time and computation time are also shorter than other algorithms, at 15.40s and 120.21s, respectively. In summary, the design of Retrieval Augmented Generation (RAG) enterprise architecture knowledge retrieval services based on improved generative…
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.