In the cloud-native environment, microservice architecture faces dual challenges: ambiguity in service configuration semantics and the reliance on manual experience for change generation. Traditional traffic limiting and resource scheduling methods suffer from static nature, insufficient global optimization, and lack of collaboration. Research Method: A microservice orchestration framework based on LLM is proposed. LLM is utilized to parse service configuration semantic information, achieving precise mapping from natural language to configuration parameters. Reinforcement learning (such as DQN model) is integrated to dynamically generate traffic limiting strategies and container resource adjustment schemes, supporting both non-interactive and interactive collaborative adjustment modes. Research Results: Under Workload1 and Workload2 loads, the request success rate is improved by an average of 57% compared to static methods and by 32%-56% compared to the SPCB algorithm. In scenarios with dynamic resource changes, the response time violation rate is further reduced through state space expansion (incorporating total resource amount and arrival rate), maximizing the request success rate. Conclusion: This framework leverages LLM semantic parsing and reinforcement learning strategies to achieve intelligent collaboration between microservice request connection limits and container resources, enhancing system stability and resource utilization. It provides a new path for cloud-native microservice orchestration.

Jiahe Chen. Construction of a Cloud-Native High-Performance Service Engineering System for Real-Time Decision-Making Platforms. International Journal of Multimedia Computing (2026), Vol. 7, Issue 1: 42-51. https://doi.org/10.38007/IJMC.2026.070106

[1] Zhong S, Rigger M. Scaling Automated Database System Testing[J].  2025.

[2] Zu E, Shu M H, Huang J C, et al. Management Problems of Modern Logistics Information System Based on Data Mining[J]. Mob. Inf. Syst.  2021, 2021:5241921:1-5241921:9. DOI:10. 1155/2021/5241921.

[3] Liu H, Zhu F, Cheng L. Proof-of-Data: A Consensus Protocol for Collaborative Intelligence[J].  2025.

[4] Ma, X. (2026). Research on End-To-End Reliability Modeling and Optimization of Service Grid.

[5] Zelin Wang. Data Analysis and Risk in Supply Chain Management. International Journal of Social Sciences and Economic Management (2026), Vol. 7, Issue 1: 132-140.

[6] Weiyao Ma. Automated Operation Approach for Scalable Cloud Data Platform. International Journal of Big Data Intelligent Technology (2026), Vol. 7, Issue 1: 131-139.

[7] Zinuo Wang. Value Reassessment Logic of Resource-Based Enterprises in the Context of Energy Transition. International Journal of Social Sciences and Economic Management (2026), Vol. 7, Issue 1: 141-149.

[8] Xiao Ma. Engineering Study of Disaster Recovery and Fault Self-Healing Mechanisms for Distributed Systems under Cross-Regional Deployment Conditions. International Journal of Engineering Technology and Construction (2026), Vol. 7, Issue 1: 1-7.

[9] Zhixian Zhang. Research on Model Engineering Integration Methods for AI Systems Based on Data-Driven Intelligence. International Journal of Big Data Intelligent Technology (2026), Vol. 7, Issue 1: 140-149.

[10] Zheng, H. (2026). Research on Edge Computing Network Task Scheduling and Resource Management Optimization Based on Artificial Intelligence Technology.

[11] Zheng, H. (2026). Research on Edge Computing Deep Neural Network Task Unloading Based on Resource Collaboration Framework and Multi Strategy Optimization.

[12] Zhang, Z. (2026). Research on the Design of Scalable Enterprise-Level AI Systems Data Platform Architectures from an SDE Perspective.

[13] Yu, X. (2026). Exploration of Multi-Channel Conversion Path Optimization Methods Based on A/B Testing.

[14] Han, X. (2026). Research on Automotive Manufacturing Process Optimization Methods for Multi-Supplier Collaboration.

[15] Hou, Y. (2026). Research on BIOS and BMC Compatibility Optimization Methods for Cross-Generation Servers in Production Environments.

[16] Yin, J. (2026). Research on Financial Time Series Prediction and Multiscale Correlation Based on the Fusion of Network Big Data and Deep Learning.

[17] Yu, X. (2026). Strategy Models and Practical Research of Growth Marketing under the Background of Digital Transformation.

[18] Yu, X. (2025). Digital Transformation Empowers Growth Marketing with Marketing Data Analysis Integration and Real-Time Display Strategy.

[19] Liu, H. (2026). Research on the Application of Causal Reasoning Method in Content Compliance Experimental Evaluation.

[20] Wang, Y. (2026). Research on the Application of Artificial Intelligence in Supply Chain Risk Early Warning.

[21] Sun, Q. (2026). Research on a Robotic Natural Language Intelligent Decision-Making Framework Based on Large Language Models, Thinking Chain Reasoning, and Multi-Agent Collaboration.

[22] Zhou, Y. (2024, November). Construction of a Multi-factor Quantitative Stock Selection System for the New Energy Industry Based on Microservices Architecture and Machine Learning Components. In International Conference on Cognitive based Information Processing and Applications (pp. 163-174). Singapore: Springer Nature Singapore.

[23] Huang, J. (2025, September). Performance Evaluation Index System and Engineering Best Practice of Production-Level Time Series Machine Learning System. In 2025 International Conference on Intelligent Communication Networks and Computational Techniques (ICICNCT) (pp. 01-07). IEEE.

[24] Hua, X. (2024, November). Design and Implementation of a Game QoE Monitoring and Evaluation System Driven by Network Traffic Analysis. In International Conference on Cognitive based Information Processing and Applications (pp. 149-161). Singapore: Springer Nature Singapore.

[25] Wu, W. (2025, June). Construction and optimization of intelligent gateway software management platform based on jenkins cluster management under cloud edge integration architecture in industrial internet of things. In International Conference on 6G Communications Networking and Signal Processing (pp. 633-645). Singapore: Springer Nature Singapore.

[26] Wu, L. (2025, December). Design and Application of Automatic Data Set Generation Tool Based on KLEE in Embedded Memory Management Performance Test Framework. In 2025 IEEE 17th International Conference on Computational Intelligence and Communication Networks (CICN) (pp. 1111-1117). IEEE.

[27] Qi, Y. (2025, October). Research on Privacy Protection of AI Models in Big Data Using Differential Privacy Technology. In 2025 2nd International Conference on Software, Systems and Information Technology (SSITCON) (pp. 1-5). IEEE.