Digital Technology Enables Accurate Supply of Grassroots Public Services Mechanism Innovation and Efficiency Evaluation

The increasing demand for personalized and efficient public service delivery requires innovative mechanisms capable of accurately matching citizen needs with available resources. This study proposes a digital-technology-enabled precision public service framework covering the complete process of demand identification, resource allocation, decision support, and feedback optimization. Multi-source data integration is employed to construct dynamic resident demand profiles, while knowledge graph techniques are used to establish semantic associations between service requirements and public resources. A digital twin simulation environment is further developed to evaluate alternative service allocation strategies before implementation. In addition, a deep-learning-based feedback analysis module continuously updates the decision model through user evaluation information. Experimental results demonstrate significant improvements in demand recognition accuracy and citizen satisfaction. The proposed framework provides methodological support for intelligent governance and offers references for information sensing, digital twin systems, and intelligent decisionmaking networks.