Big Data, AI, and Multi-algorithm Fusion Empower the Modeling and Optimization of Digital Service Systems

作者：Pengzhao Du, Yuhan Zhang, Lili Jin · 发表于：Procedia Computer Science · 年份：2026 · DOI：10.1016/j.procs.2026.04.289 · 研究领域：Digital Transformation in Industry、Internet of Things and AI、Impact of AI and Big Data on Business and Society

Against the backdrop of rapid development in the digital economy, digital service systems face pain points such as fragmented multi-source heterogeneous data, insufficient adaptability of single algorithms, and low efficiency in service link collaboration, making it difficult to meet users’ personalized and efficient service needs. Addressing the issues of insufficient data fusion accuracy, lack of flexibility in algorithm selection, and optimization focusing only on localized aspects in current digital service modeling, which hinders improvements in service quality and user experience, this paper proposes an empowering architecture that integrates big data and AI multi-algorithms. First, a multi-source heterogeneous data fusion framework and a digital service knowledge graph are constructed to achieve unified integration and knowledge-based representation of data resources. Second, a multi-algorithm fusion engine based on "filtering-prediction-decision" is designed, leveraging the complementary advantages of collaborative filtering, long short-term memory networks, and deep reinforcement learning to overcome the limitations of single algorithms. Finally, a global optimization algorithm for the service link is proposed to achieve collaborative optimization throughout the entire service process. The experiment selected three typical digital service scenarios—government services, e-commerce services, and medical services—for testing. The results showed that the proposed model a...