
基于网格化管理事件大数据的上海市气象与城市运行体征关联规则挖掘
Mining of association rules between meteorological and urban operation signs based on grid management events big data in Shanghai City
基于时空特征分析、共现词项特征分析、相关性分析及频繁模式挖掘方法对城市运行管理大数据进行分析研究,得到触发网格化管理事件发生的典型气象条件,并构建涵盖气象条件的典型网格化管理事件知识图谱。结果表明,网格化管理件发生时间与工作时间高度吻合,发生区域也与城市人员密集区相重合,类别上存在“头部集中、长尾分布”的现象,网格化管理事件分词上可以形成较为清晰的聚类结构,形成以市民活动为主体的共现词项关系网络。结合气象资料分析,市政设施、环卫等小类与气温相关性较为明显,风易损结构受风力影响较大,并且在降水、低温、高温和大风等特定天气情况下基坑、纠纷类、高空抛物和河道绿化等事件将呈现高发趋势。此外,通过采用知识图谱技术归纳和表达气象与城市运行之间的关联,从而有利于城市运行管理人员在特定天气条件的提前应对和处置。
Refinement governance is the future governance direction of the city, and it is also an important challenge for Shanghai to build an outstanding global city. Most of the existing research is based on the innovative mode and management mechanism of urban grid management, but the analysis and mining of grid management event data are still insufficient, and there is a lack of regular analysis of meteorological conditions on the occurrence of events. From the meteorological perspective, this paper uses spatiotemporal feature analysis and natural language processing methods to analyze the features of grid management event data, and uses correlation analysis and frequent pattern mining algorithms to obtain the association rules between meteorological conditions and urban management events. On this basis, the typical meteorological conditions that trigger grid management events are obtained, and the typical event knowledge graph covering meteorological conditions is constructed. The results show that the events are highly correlated with the characteristics of residents’ activities, the occurrence time of events is highly consistent with the working time, and the occurrence area also coincides with the densely populated areas of the city. There is a phenomenon of “concentrated head and long tail distribution” in the category, and a clear clustering structure can be formed in the event word segmentation, forming a co-occurrence term relation network with citizen activities as the main body. Analysis with meteorological data, municipal facilities and sanitation categories have obvious correlations with air temperature, wind-vulnerable structures are greatly affected by wind, and some illegal behaviors are also highly correlated with meteorological conditions. In addition, under specific weather conditions, some events will show an obvious tendency to occur easily. For example, events such as foundation pits, disputes, high-altitude parabolas, and river greening occur under specific weather conditions such as precipitation, low temperature, high temperature and strong wind, and strong winds will also have an amplified effect on environmental problems such as river pollution, open burning and the distribution of leaflet. On this basis, the knowledge graph technology is used to summarize and express the relationship between meteorology and urban operation, so as to form a knowledge framework for urban operation signs triggered by meteorological conditions, which is beneficial for urban operation managers to respond and deal with specific weather conditions in advance, and provide certain decision-making references for Shanghai to improve refined management measures and optimize the urban governance system.
网格化管理 / 气象 / 特征挖掘 / FP-Growth / 知识图谱 {{custom_keyword}} /
grid management / meteorology / feature mining / FP-Growth / knowledge graph {{custom_keyword}} /
表1 基于24 h统计特征的上海市特定天气条件易发网格化管理事件的频繁模式挖掘结果Table 1 Frequent patterns of specific weather-condition-prone grid management events based on 24-hour statistical features in Shanghai City |
类型 | 气象条件 | 易发网格化管理事件 | 置信度 | 支持度 |
降水 | 0.1~10 mm | 基坑 | 1.00 | 0.41 |
违规占用地下公共人行通道 | 1.00 | 0.33 | ||
路面积水、污水冒溢、粪便冒溢 | 1.00 | 0.32 | ||
街头座椅 | 1.00 | 0.32 | ||
架空线隐患 | 1.00 | 0.31 | ||
最低 气温 | 0~10 ℃ | 纠纷类 | 0.61 | 0.44 |
市场经营 | 0.84 | 0.42 | ||
公共场所消防安全隐患 | 1.00 | 0.41 | ||
灭火器 | 0.85 | 0.41 | ||
综合杆 | 0.87 | 0.33 | ||
流浪乞讨 | 0.98 | 0.32 | ||
违法搭建 | 0.89 | 0.31 | ||
老人关怀 | 0.83 | 0.31 | ||
自来水管破裂 | 1.00 | 0.30 | ||
最高 气温 | 30~35 ℃ | 维稳重点点位管理 | 0.96 | 0.41 |
高空抛物 | 0.90 | 0.32 | ||
居住区设施设备不规范 | 0.98 | 0.31 | ||
小区内垃圾 | 0.86 | 0.31 | ||
最大 风速 | (5.4~ 10.7)m/s | 公安井盖 | 1.00 | 0.49 |
树穴盖板损坏 | 0.74 | 0.49 | ||
路灯井盖 | 0.77 | 0.47 | ||
河道污染 | 0.74 | 0.47 | ||
景观灯光设施 | 1.00 | 0.46 | ||
露天焚烧 | 0.79 | 0.46 | ||
消防井盖 | 0.76 | 0.46 | ||
乱设摊 | 0.72 | 0.46 | ||
雨水篦子 | 1.00 | 0.45 | ||
跨门营业 | 0.81 | 0.45 | ||
渣土车管理 | 0.80 | 0.45 | ||
交通立杆 | 0.78 | 0.45 | ||
街面秩序 | 0.74 | 0.45 | ||
无障碍标牌 | 0.69 | 0.45 | ||
非机动车安全管理 | 1.00 | 0.44 | ||
机非分隔设施 | 1.00 | 0.44 | ||
灭火器 | 0.89 | 0.44 | ||
架空线隐患 | 0.79 | 0.44 | ||
农业垃圾乱处置 | 0.76 | 0.44 | ||
河道绿化 | 0.73 | 0.44 | ||
河道护栏 | 0.68 | 0.44 | ||
综合杆 | 0.68 | 0.44 | ||
市政立杆 | 1.00 | 0.43 | ||
小区绿化 | 1.00 | 0.43 | ||
高空抛物 | 0.85 | 0.43 | ||
路中分隔设施 | 0.82 | 0.43 | ||
交通信号灯 | 0.80 | 0.43 | ||
电力杆 | 0.79 | 0.43 | ||
违法搭建 | 0.73 | 0.43 | ||
公益广告损坏 | 0.67 | 0.43 | ||
垃圾箱房 | 1.00 | 0.42 | ||
电力井盖 | 0.81 | 0.42 | ||
路名牌 | 0.81 | 0.42 | ||
污水井盖 | 0.86 | 0.41 | ||
街头散发小广告 | 0.83 | 0.41 | ||
道路指示牌 | 0.8 | 0.41 | ||
架空线坠落 | 0.77 | 0.41 | ||
小区环境 | 1.00 | 0.40 | ||
花架花钵 | 1.00 | 0.40 | ||
宣传栏(亭) | 0.82 | 0.40 | ||
路灯 | 0.81 | 0.40 |
[1] |
叶岚. 城市网格化管理的制度化进程及其优化路径[J]. 上海行政学院学报, 2018, 19(4): 27-38.
Ye Lan. Institutionalization process of grid management and its optimized path. The Journal of Shanghai Administration Institute, 2018, 19(4): 27-38.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[2] |
吴青熹. 基层社会治理中的政社关系构建与演化逻辑——从网格化管理到网络化服务[J]. 南京大学学报(哲学·人文科学·社会科学), 2018, 55(6): 117-125.
Wu Qingxi. The construction and evolution logic of government-social relations in grassroots social governance—From grid management to grid service. Journal of Nanjing University (Philosophy, Humanities and Social Sciences), 2018, 55(6): 117-125.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[3] |
常燕军, 周向红. 基于ARIMA模型的城市网格化管理预测与仿真[J]. 统计与决策, 2016(1): 54-57.
Chang Yanjun Zhou Xianghong. Prediction and simulation of urban grid management based on ARIMA model. Statistics & Decision, 2016(1): 54-57.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[4] |
刘伟, 王柏秀. 国内学界的网格化管理研究: 回顾、反思与展望[J]. 公共管理与政策评论, 2022, 11(1): 157-168.
Liu Wei, Wang Baixiu. Grid management research in China: Review, reflection and prospect. Public Administration and Policy Review, 2022, 11(1): 157-168.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[5] |
王雪竹. 基层社会治理: 从网格化管理到网络化治理[J]. 理论探索, 2020(2): 76-80.
Wang Xuezhu. Grassroots social governance: From grid management to grid governance. Theoretical Exploration, 2020(2): 76-80.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[6] |
董幼鸿. 大城市基层综合治理机制创新的路径选择——以上海城市网格化管理和联动联勤机制建设为例[J]. 上海行政学院学报, 2015, 16(6): 31-37.
Dong Youhong. The path choices of the innovation of basic comprehensive governance mechanism in big cities. The Journal of Shanghai Administration Institute, 2015, 16(6): 31-37.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[7] |
彭晓, 梁艳, 许立言, 等. 基于“12345”市民服务热线的城市公共管理问题挖掘与治理优化途径[J]. 北京大学学报(自然科学版), 2020, 56(4): 721-731.
Peng Xiao, Liang Yan, Xu Liyan et al. An approach for discovering urban public management problem and optimizing urban governance based on ''12345''citizen service hotline. Acta Scientiarum Naturalium Universitatis Pekinensis, 2020, 56(4): 721-731.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[8] |
王杰艺. 城市网格管理事件模式挖掘与预测[D]. 上海: 上海交通大学, 2018.
Wang Yijie. Urban grid management incidents pattern mining and prediction. Shanghai: Shanghai Jiao Tong University, 2018.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[9] |
张良, 秦雪. 基于气象的特大城市运行风险治理多层次联动响应体系研究——以上海市徐汇区为例[J]. 风险灾害危机研究, 2020(1): 169-188.
Zhang Liang, Qin Xue. Research on multi-level linkage response system for operational risk management of megacities based on meteorology: Taking Xuhui district of Shanghai as an example. Journal of Risk, Disaster & Crisis Research, 2020(1): 169-188.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[10] |
杨辰, 潘顺, 严岩. 基于自然语言识别的上海市报警灾情数据识别及其气象灾害特征分析研究[J]. 自然灾害学报, 2021, 30(3): 142-150.
Yang Chen, Pan Shun, Yan Yan. Research on recognition of alarm disaster data and analysis of meteorological disaster features in Shanghai based on natural language recognition algorithm. Journal of Natural Disaster, 2021, 30(3): 142-150.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[11] |
杨辰, 王强, 李海宏, 等. 基于频繁模式挖掘的上海市气象灾害致灾因子识别[J]. 灾害学, 2023, 38(2): 141-149.
Yang Chen, Wang Qiang, Li Haihong et al. Identification of meteorological disasters factors in Shanghai based on frequent pattern mining. Journal of Catastrophology, 2023, 38(2): 141-149.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[12] |
Wang Y, Wang T, Ye X et al. Using social media for emergency response and urban sustainability: A case study of the 2012 Beijing Rainstorm[J]. Sustainability, 2016, 8(1): 25.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[13] |
林筱妍, 吴升. 基于语义规则和词向量的台风灾害网络情感分析方法[J]. 地球信息科学学报, 2022, 24(1): 114-126.
Lin Xiaoyan, Wu Sheng. Typhoon disaster network emotion analysis method based on semantic rules and word vector. Journal of Geo-information Science, 2022, 24(1): 114-126.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[14] |
高雁鹏, 陈文俊. 1984—2020年辽宁省极端气温时空变化及粮食产量响应研究[J]. 地理科学, 2021, 41(11): 2052-2062.
Gao Yanpeng, Chen Wenjun. Spatial and temporal variation of extreme temperature and grain yield response in Liaoning Province from 1984 to 2020. Scientia Geographica Sinica, 2021, 41(11): 2052-2062.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[15] |
Bi H, Ye Z, Zhu H. Data-driven analysis of weather impacts on urban traffic conditions at the city level[J]. Urban Climate, 2022, 41: 101065.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[16] |
Park J, Choi Y, Chae Y. Heatwave impacts on traffic accidents by time-of-day and age of casualties in five urban areas in South Korea[J]. Urban Climate, 2021, 39: 100917.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[17] |
李莹, 高歌, 程驰. 影响中国高速铁路运行的暴雨危险性特征研究[J]. 地理科学, 2021, 41(10): 1843-1851.
Li Ying, Gao Ge, Cheng Chi. Hazard intensity of rainstorm affecting high-speed railway operation in China. Scientia Geographica Sinica, 2021, 41(10): 1843-1851.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[18] |
任永建, 熊守权, 洪国平, 等. 气象因子对夏季最大电力负荷的敏感性分析[J]. 气象, 2020, 46(9): 1245-1253.
Ren Yongjian, Xiong Shouquan, Hong Guoping et al. Sensitivity analysis of meteorological factors to summer maximum power load. Meteorological Monthly, 2020, 46(9): 1245-1253.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[19] |
薛阳, 张宁, 吴海东, 等. 基于UTCI-MIC与振幅压缩灰色模型的用户侧微电网短期负荷预测方法[J]. 电网技术, 2020, 44(2): 556-563.
Xue Yang, Zhang Ning, Wu Haidong et al. Short-term load forecasting method for user side microgrid based on UTCI-MIC and amplitude compression grey model. Power System Technology, 2020, 44(2): 556-563.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[20] |
何春蕾, 段言志, 邬宗婧, 等. 基于气温的城市燃气短期日负荷预测模型——以四川省成都地区为例[J]. 天然气工业, 2013, 33(4): 131-134.
He Chunlei, Duan Yanzhi, Wu Zongjing et al. A short-term forecasting model of city gas daily load based on air temperature. Natural Gas Industry, 2013, 33(4): 131-134.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[21] |
Salton G, Buckley C. Term-weighting approaches in automatic text retrieval[J]. Information Processing & Management, 1988, 24(5): 513-523.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[22] |
Han J, Pei J, Yin Y. Mining frequent patterns without candidate generation[C]//Maggie D, Jeffrey F. Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, May 16-18, 2000, Dallas, Texas, USA, ACM. New York: Association for Computing Machinery, 2000. DOI:10.1145/342009.335372.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[23] |
来斯惟,徐立恒,陈玉博,等.基于表示学习的中文分词算法探索[J].中文信息学报,2013,27(5):8-14. Lai Siwei, Xu Liheng, Chen Yubo et al. Chinese word segment based on character representation learning. Journal of Chinese Information Processing, 2013, 27(5): 8-15.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[24] |
Rabiner L R. A tutorial on hidden Markov models and selected applications in speech recognition[J]. Proceedings of the IEEE, 1989, 77(2): 257-286.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[25] |
Han J W, Kamber M, Pei J. 数据挖掘: 概念与技术( 第3版)[M]. 范明, 等译. 北京: 机械工业出版社, 2017.
Han J W, Kamber M, Pei J. Data mining: Concepts and techniques (Third Edition). Translated by Fan Ming et al. Beijing: China Machine Press, 2017.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[26] |
Han J, Pei J, Yin Y et al. Mining frequent patterns without candidate generation: A frequent-pattern tree approach[J].Data Mining and Knowledge Discovery, 2004, 8: 53-87.DOI: 10.1023/B:DAMI.0000005258.31418.83.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[27] |
杜梦欣. 基于FP-Growth的关联规则算法研究及其在高校教育大数据中的应用[D]. 长春: 吉林大学, 2019.
Du Mengxin. Research on association rules algorithm based on FP-Growth and its application in university education big data. Changchun: Jilin University, 2019.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[28] |
顾军华, 武君艳, 许馨匀, 等. 基于Spark的并行FP-Growth算法优化及实现[J]. 计算机应用, 2018, 38(11): 3069-3074.
Gu Junhua, Wu Junyan, Xu Xinyun et al. Optimization and implementation of parallel FP-Growth algorithm based on Spark. Journal of Computer Applications, 2018, 38(11): 3069-3074.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[29] |
周强明, 姜盛波, 鲁鸿毅, 等. 基于FP-Growth算法的大电网关键线路辨识方法[J]. 电力自动化设备, 2018, 38(4): 89-95.
Zhou Qiangming, Jiang Shengbo, Lu Hongyi et al. Critical line identification method based on FP-Growth algorithm for large power grid. Electric Power Automation Equipment, 2018, 38(4): 89-95.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[30] |
肖仰华. 知识图谱概念与技术[M]. 北京: 电子工业出版社, 2020.
Xiao Yanghua. Knowledge graph: Concepts and techniques. Beijing: Publishing House of Electronics industry, 2020.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
[31] |
马昂, 于艳华, 杨胜利, 等. 基于强化学习的知识图谱综述[J]. 计算机研究与发展, 2022, 59(8): 1694-1722.
Ma Ang, Yu Yanhua, Yang Shengli et al. Survey of knowledge graph based on reinforcement learning. Journal of Computer Research and Development, 2022, 59(8): 1694-1722.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
〈 |
|
〉 |