面向城市可持续发展的城市商圈/街区知识图谱构建方法与应用展望
刘 宇(1995— ),男,内蒙古鄂尔多斯人,博士生,主要从事知识图谱和城市计算研究。E-mail: liuyu2419@126.com |
收稿日期: 2023-05-13
修回日期: 2023-09-11
网络出版日期: 2023-12-05
基金资助
国家自然科学基金项目(U22B2057)
国家重点研发计划项目(2020AAA0106000)
Methodology for Constructing Urban Business Area/Region Knowledge Graph and the Applications in Urban Sustainable Development
Received date: 2023-05-13
Revised date: 2023-09-11
Online published: 2023-12-05
Supported by
National Natural Science Foundation of China(U22B2057)
National Key Research and Development Program of China(2020AAA0106000)
城市正在成为人类社会可持续发展的核心要素。随着大数据和人工智能技术的飞速发展,越来越多的研究致力于数据驱动的城市可持续发展,通过海量多源异构城市数据对城市在社会、经济和生态方面的可持续发展进程进行监测、解释和评估。然而,当前研究往往局限在单一应用场景和单一数据源,缺少对不同城市数据源、不同城市元素之间内在关联的考虑,难以泛化到城市可持续发展的多种场景。因此,本文提出城市商圈/街区知识图谱驱动的城市可持续发展研究框架。首先,从海量多源异构城市数据中构建城市商圈/街区知识图谱本体,建模人、地、组织、商圈和街区等城市元素的关联关系,进一步在本体指导下实现知识融合,构建城市商圈/街区知识图谱。紧接着,围绕城市可持续发展进程的状态监测、现象解释和决策评估介绍城市商圈/街区知识图谱驱动的城市可持续发展应用。最后,以城市社会经济指标预测为典型任务,提出知识注入的跨模态对比学习方案,验证城市商圈/街区知识图谱在相关应用中的有效性和泛化性,为城市商圈/街区知识图谱驱动的城市可持续发展提供典型例证。
刘宇 , 李勇 . 面向城市可持续发展的城市商圈/街区知识图谱构建方法与应用展望[J]. 地球信息科学学报, 2023 , 25(12) : 2374 -2386 . DOI: 10.12082/dqxxkx.2023.230262
Nowadays, cities have emerged as one of the core elements for the sustainable development of human society. This also aligns well with the United Nations Sustainable Development Goals on sustainable cities. The pivotal role of cities is also demonstrated by the rapid development of big data and artificial intelligence technologies. There have been more and more studies dedicated to the realm of data-driven urban sustainability, in which the complex processes of urban sustainable development, encompassing social, economic, and ecological dimensions, are monitored, interpreted, and evaluated through massive urban data from multiple sources. However, a common limitation is that most existing studies concentrate on individual application scenarios and singular data sources and ignore the intricate interconnections among diverse urban data sources and multiple urban elements, making it challenging to explore findings across diverse urban sustainability contexts. Therefore, to address this critical gap, in this paper, we propose a novel approach for urban sustainable development driven by Urban Business Area/Region Knowledge Graph (UKG). This approach incudes two fundamental steps: the construction of a comprehensive ontology for the UKG based on massive multi-source urban data, and the subsequent synthesis of knowledge guided by this ontology to create the UKG. The construction of the UKG ontology captures important elements in cities as well as their complex interconnections, e.g., people, locations, and organizations, and their relationships in terms of spatiality, function, and association. This ontological architecture lays the foundation for the subsequent knowledge fusion, ultimately leading to the construction of UKG. The practical applications of UKG in driving urban sustainability are manifold, ranging from real-time status monitoring and nuanced interpretation of urban phenomena to the holistic evaluation of decisions made for urban sustainability. To verify the effectiveness and efficiency of the proposed approach, the paper introduces a novel cross-modality contrastive learning framework that incorporates semantic knowledge for urban sustainability. The proposed framework includes a semantic encoder and a visual encoder to capture information from UKG and urban images (satellite images and street view images), respectively. Based on the assumption that the semantic representation of UKG entities should be close to their corresponding image representations, the proposed framework successfully incorporate semantic knowledge into visual encoder, which further enhances the predictive capabilities of urban socioeconomic indicators derived from urban images. Through empirical validation, this study demonstrates the real-world applicability and generalizability of the UKG framework for urban sustainability.
表1 城市商圈/街区知识图谱驱动的城市可持续发展应用概览Tab. 1 The overview of urban business area/region knowledge graph-driven urban sustainability applications |
应用概览 | 社会方面 | 经济方面 | 生态方面 |
---|---|---|---|
节点级别 | 个体就业/学历/健康监测、 区域人口/就业监测、 …… | 个体收入情况监测、 店铺营收情况监测、 区域经济监测与解释、 …… | 区域绿化监测与解释、 区域韧性监测与评估、 …… |
子图级别 | 城中村识别与解释 …… | 功能区产业结构监测、 行政区经济水平监测、 …… | 碳排放监测与评估、 用地规划与评估、 …… |
表2 城市多源异构数据集Tab. 2 Summary of multi-source heterogeneous urban datasets |
数据集 | 数据来源 | 数据内容 | 记录数/条 |
---|---|---|---|
路网数据集 | 地图平台 | 路网标识、路网对应的经纬度坐标序列 | 2 523 |
地点数据集 | 地图平台 | 地点标识、名称、地址、经纬度坐标及所属类别 | 1 618 604 |
商圈数据集 | 生活服务平台 | 商圈标识、名称、中心经纬度坐标 | 365 |
组织数据集 | 百科文档 | 组织标识、组织名称 | 2 001 |
轨迹数据集 | 移动运营商 | 用户标识、经纬度坐标点、时间戳 | 447 061 |
画像数据集 | 问卷调查 | 用户标识、属性名称、属性值 | 4 255 |
遥感数据集 | ArcGis | 遥感图像标识、对应网格经纬度、遥感图像 | 300 663 |
街景数据集 | 地图平台 | 街景图像标识、对应拍摄经纬度、街景图像 | 112 859 |
表3 城市商圈/街区知识图谱不同类型实体数Tab. 3 The number of entities by types in urban business area/region knowledge graph (个) |
人 | 地点 | 组织 | 街区 | 商圈 | 类别 | |
---|---|---|---|---|---|---|
北京市 | 51 089 | 1 481 100 | 1 545 | 1 900 | 333 | 437 |
表4 城市商圈/街区知识图谱不同类型关系实例数Tab. 4 The number of facts by relation types in urban business area/region knowledge graph (个) |
关系类型 | 实例数量 | 关系类型 | 实例数量 |
---|---|---|---|
位于 | 1 481 100 | 组织所属类别(细) | 1 545 |
归属 | 1 256 591 | 类别从属 | 5 273 |
街区交界 | 10 126 | 居住地位于 | 47 269 |
街区邻近 | 20 902 | 工作地位于 | 36 863 |
服务辐射 | 8 392 | 访问 | 712 462 |
隶属组织 | 99 797 | 街区流量转移 | 297 040 |
地点所属类别(粗) | 1 481 100 | 街区功能相似 | 4 254 |
地点所属类别(中) | 1 481 100 | 相关组织 | 578 |
地点所属类别(细) | 1 481 100 | 竞争 | 11 830 |
组织所属类别(粗) | 1 870 | 共现 | 291 951 |
组织所属类别(中) | 1 858 | 部署于 | 25 037 |
表5 基于城市图像的社会经济指标预测性能比较Tab. 5 Result comparison of urban imagery-based socioeconomic indicator prediction |
模型 | 人口 | 商业活跃度 | 餐饮业活跃度 | 消费能力 | ||||
---|---|---|---|---|---|---|---|---|
RMSE | RMSE | RMSE | RMSE | |||||
KnowCL | 0.523 | 0.720 | 0.587 | 1.033 | 0.646 | 0.823 | 0.417 | 2.805 |
本文 | 0.556 | 0.695 | 0.598 | 1.019 | 0.692 | 0.768 | 0.423 | 2.789 |
[1] |
|
[2] |
|
[3] |
|
[4] |
|
[5] |
|
[6] |
|
[7] |
United Nations. Department of Economic and Social Affairs. The sustainable development goals: Report 2022[M]. UN, 2022.
|
[8] |
|
[9] |
|
[10] |
|
[11] |
|
[12] |
|
[13] |
|
[14] |
|
[15] |
|
[16] |
|
[17] |
|
[18] |
|
[19] |
刘知远, 孙茂松, 林衍凯, 等. 知识表示学习研究进展[J]. 计算机研究与发展, 2016, 53(2):247-261.
[
|
[20] |
|
[21] |
|
[22] |
|
[23] |
王晓爽, 李吉东, 徐海红, 等. 顾及时空特征的大气污染执法事理图谱构建方法研究[J]. 地理与地理信息科学, 2022, 38(3):1-8.
[
|
[24] |
高嘉良, 陆锋, 彭澎, 等. 基于网络文本迁移学习的旅游知识图谱构建[J]. 武汉大学学·报信息科学版, 2022, 47(8):1191-1200,1219.
[
|
[25] |
|
[26] |
|
[27] |
|
[28] |
|
[29] |
|
[30] |
诸云强, 孙凯, 胡修棉, 等. 大规模地球科学知识图谱构建与共享应用框架研究与实践[J]. 地球信息科学学报, 2023, 25(6):1215-1227.
[
|
[31] |
|
[32] |
|
[33] |
|
[34] |
李善平, 尹奇韡, 胡玉杰, 等. 本体论研究综述[J]. 计算机研究与发展, 2004, 41(7):1041-1052.
[
|
[35] |
|
[36] |
徐增林, 盛泳潘, 贺丽荣, 等. 知识图谱技术综述[J]. 电子科技大学学报, 2016, 45(4):589-606.
[
|
[37] |
|
[38] |
|
[39] |
|
[40] |
|
[41] |
|
[42] |
|
[43] |
|
[44] |
|
[45] |
|
/
〈 | 〉 |