Optimization and Effectiveness Evaluation of Digital Empowerment for Collaborative Governance of Grassroots Public Services

Current grassroots public-service systems face challenges associated with fragmented data resources, low crossdepartment collaboration efficiency, and insufficient decision-support capability. This study proposes a data-driven collaborative governance framework integrating multi-source data fusion, intelligent analytics, and dynamic feedback mechanisms. A three-stage architecture consisting of data-resource integration, intelligent decision support, and collaborative execution is developed. Distributed data collection, federated learning, machine-learning-based prediction, and natural-language-processing-assisted feedback analysis are employed to enable real-time information sharing and adaptive governance optimization. Experimental results demonstrate substantial improvements in service-processing efficiency, collaborative response capability, and user satisfaction. The proposed framework provides an effective solution for intelligent decision support and large-scale information-system coordination.