Construction of Data-Driven Urban Conflict Prevention and Governance Model
Yiwen Liu
What the paper says
The surge of urban operation data provides a new opportunity for prior identification and accurate intervention of contradictions and disputes. Based on the data of 12,345 work orders, police receiving, and judicial mediation in a sub-provincial city in recent three years, this paper constructs a closed-loop model of “perception-prediction- intervention-feedback”: it opens up semantic mapping and synchronization of cross-departmental heterogeneous data, integrates multi-scale spatio-temporal characteristics, and embeds LightGBM-Text cellular neural network (CNN) dual-channel model to realize minute-level prediction, differentiate intervention according to risk level, and optimize the closed-loop through visual dashboard. The six-month A/B test shows that the dispute response time is shortened by 36.9%, the incident resolve rate is increased by 22.6%, and the satisfaction of the masses is increased by 18.1%. Under the premise of clear responsibilities, the model realizes efficient multi-sectoral linkage and adaptive governance and provides a replicable paradigm for social governance in megacities.
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.50 × 0.4 = 0.20 |
| M · momentum | 0.50 × 0.15 = 0.07 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.