Conflict measurement in complex networks of Yellow River ecological governance based on knowledge graph and R-GAT model

doi:10.11996/JG.j.2095-302X.2026051125

Abstract

Abstract:

Ecological governance in the Yellow River Basin involves coordinating multiple agents, tasks, and mechanisms. Multi-source texts including policy documents, corporate reports, and public-opinion texts contain numerous implicit governance relationships and clues regarding conflict transmission. Converting this information into computable graph structures to identify and measure conflicts represents a key challenge in complex network governance analysis. To address the limitations of existing methods in organizing unstructured governance semantics, expressing conflict topology, and quantifying conflict intensity, a complex network conflict measurement method integrating knowledge graphs with Relational Graph Attention Networks (R-GAT) was proposed, drawing on approaches to complex-object modeling, topological relationship representation, and visual analysis in graphics. The semantic structures and directed relational networks provided by knowledge graphs were used as structural foundations and semantic priors for R-GAT, through which, through which the impact intensity of different relational edges on conflict formation, were learned and complex governance relationships were transformed from textual semantics into graph structures, topological analysis, and quantitative measurement. Experimental results demonstrated favorable performance in ranking conflict intensity and identifying strong conflict relationships, and key conflict relationships within the complex network of Yellow River ecological governance were effectively identified. A knowledge-graph-driven graph-learning method was thereby provided for graph-structural modeling of complex relational objects and multi-agent governance conflict measurement.

Key words: complex network, polycentric ecological governance, knowledge graph, conflict measurement

CLC Number:

XU Jiaming, CHEN Guangyao, XU Zhao. Conflict measurement in complex networks of Yellow River ecological governance based on knowledge graph and R-GAT model[J]. Journal of Graphics, 2026, 47(5): 1125-1134.

Figures/Tables 13

References 26

[1]	李伟涛. 跨域协同视角下黄河流域生态治理的困境与突破[J]. 生态经济, 2025, 41(11): 230-231.
	LI W T. The dilemma and breakthrough of ecological governance in the Yellow River Basin from the perspective of cross-domain collaboration[J]. Ecological Economy, 2025, 41(11): 230-231 (in Chinese).
[2]	宫长瑞, 张乃亮. 黄河流域生态环境数字化治理的图景、困境与路径[J]. 河南社会科学, 2025, 33(7): 91-98.
	GONG C R, ZHANG N L. The prospects, dilemmas and pathways of digital governance for the ecological environment in the Yellow River Basin[J]. Henan Social Sciences, 2025, 33(7): 91-98 (in Chinese).
[3]	杨欣谊, 杨建林, 叶文豪. 基于异质信息网络的领域知识簇网络特征分析[J]. 情报学报, 2025, 44(9): 1128-1143.
	YANG X Y, YANG J L, YE W H. Network characterization of domain knowledge clusters based on heterogeneous information network[J]. Journal of the China Society for Scientific and Technical Information, 2025, 44(9): 1128-1143 (in Chinese).
[4]	何柳, 安然, 刘姝妍, 等. 基于知识图谱的航空多模态数据组织与知识发现技术研究[J]. 图学学报, 2024, 45(2): 300-307. DOI
	HE L, AN R, LIU S Y, et al. Research on knowledge graph-based aviation multi-modal data organization and discovery method[J]. Journal of Graphics, 2024, 45(2): 300-307 (in Chinese). DOI
[5]	闫志华, 唐锡晋. 面向冲突事件的事件知识图谱构建与分析研究[J]. 系统科学与数学, 2026, 46(1): 1-16. DOI
	YAN Z H, TANG X J. Research on construction and analysis of event-centric knowledge graph for conflict events[J]. Journal of Systems Science and Mathematical Sciences, 2026, 46(1): 1-16 (in Chinese). DOI
[6]	李亚聪, 刘皓冰, 蒋若冰, 等. 异质图表征学习综述[J]. 软件学报, 2025, 36(6): 2794-2826.
	LI Y C, LIU H B, JIANG R B, et al. Survey on heterogeneous graph representation learning[J]. Journal of Software, 2025, 36(6): 2794-2826 (in Chinese).
[7]	李燕凌, 陈梦雅. 基层应急管理多元主体协同网络分析及优化策略--以长沙市基层应急协同网络为例[J]. 灾害学, 2026, 41(1): 164-170.
	LI Y L, CHEN M Y. Analysis and optimization strategies of the collaborative network of multiple subjects in grassroots emergency management: taking Changsha city as an example[J]. Journal of Catastrophology, 2026, 41(1): 164-170 (in Chinese).
[8]	屈建伸, 章紫微, 董斌, 等. 基于MSPA与复杂网络理论的浙江省森林生态网络构建及韧性评估[EB/OL]. (2026-04-16) [2026-04-24]. https://link.cnki.net/urlid/32.1161.S.20260416.1348.003.
	QU J S, ZHANG Z W, DONG B, et al. The construction of forest ecological network and resilience assessment under multiple scenario attacks in Zhejiang Province[EB/OL]. (2026-04-16) [2026-04-24]. https://link.cnki.net/urlid/32.1161.S.20260416.1348.003(in Chinese).
[9]	魏金阳, 周丽华, 王丽珍. 异质网络中融合多种语义关系的高效社区搜索方法[J]. 哈尔滨工业大学学报, 2026, 58(1): 106-118.
	WEI J Y, ZHOU L H, WANG L Z. Efficient community search with multiple semantic relationships in heterogeneous information networks[J]. Journal of Harbin Institute of Technology, 2026, 58(1): 106-118 (in Chinese).
[10]	翟洁, 陈乐旋, 庞智玉. 基于图神经网络的学业表现预测方法研究综述[J]. 计算机科学, 2026, 53(2): 16-30. DOI
	ZHAI J, CHEN L X, PANG Z Y. Survey on graph neural network-based methods for academic performance prediction[J]. Computer Science, 2026, 53(2): 16-30 (in Chinese). DOI
[11]	马续补, 张阁静, 李波, 等. 基于多要素语义关联的政策知识图谱构建[J]. 情报理论与实践, 2025, 48(8): 93-104. DOI
	MA X B, ZHANG G J, LI B, et al. Policy knowledge graph construction based on multi-factor semantic relevance[J]. Information Studies: Theory & Application, 2025, 48(8): 93-104 (in Chinese).
[12]	安宁, 安璐. 跨平台网络舆情知识图谱构建及对比分析[J]. 情报科学, 2022, 40(3): 159-165.
	AN N, AN L. Construction and comparison of cross-platform online public opinion knowledge graph[J]. Information Science, 2022, 40(3): 159-165 (in Chinese).
[13]	左屿琪, 张云峰, 张秋悦, 等. 基于超图表示学习和Transformer模型优化的知识感知推荐[J]. 图学学报, 2025, 46(5): 1050-1060. DOI
	ZUO Y Q, ZHANG Y F, ZHANG Q Y, et al. Knowledge-aware recommendation based on hypergraph representation learning and Transformer model optimization[J]. Journal of Graphics, 2025, 46(5): 1050-1060 (in Chinese). DOI
[14]	王静红, 郑瑞策, 米据生, 等. 基于结构学习和自监督图注意力的网络表示学习[J]. 山西大学学报(自然科学版), 2025, 48(1): 29-42.
	WANG J H, ZHENG R C, MI J S, et al. Network representation learning based on structural learning and self-supervised graph attention[J]. Journal of Shanxi University (Natural Science Edition), 2025, 48(1): 29-42 (in Chinese).
[15]	邓云峰, 冯永康, 王双燕. 应急决策文本的多维语义挖掘方法--基于TF-IDF和PMI的技术框架[J]. 中国安全生产科学技术, 2025, 21(5): 36-45.
	DENG Y F, FENG Y K, WANG S Y. Multidimensional semantic extract method for emergency decision-making texts: a technical framework based on TF-IDF and PMI[J]. Journal of Safety Science and Technology, 2025, 21(5): 36-45 (in Chinese).
[16]	HE Y L, WANG P F, ZHU Q X. Improved Bi-LSTM with distributed nonlinear extensions and parallel inputs for soft sensing[J]. IEEE Transactions on Industrial Informatics, 2024, 20(3): 3748-3755. DOI URL
[17]	叶航, 柴春来, 张思赟, 等. 基于BERT和Bi-LSTM的题目难度预测: 知识点标签增强模型[J]. 计算机应用, 2025, 45(S1): 37-42.
	YE H, CHAI C L, ZHANG S Y, et al. Knowledge point tag enhancement model for problem difficulty prediction based on BERT and Bi-LSTM[J]. Journal of Computer Applications, 2025, 45(S1): 37-42 (in Chinese).
[18]	张瑞, 马远, 常金雨. 基于SNA与CNN-BiLSTM-Attention组合模型的中国省域能源消费减排路径[J]. 环境科学, 2026, 47(1): 47-63.
	ZHANG R, MA Y, CHANG J Y. China's inter-provincial energy consumption emission reduction path based on SNA and CNN-BiLSTM-attention combined model[J]. Environmental Science, 2026, 47(1): 47-63 (in Chinese).
[19]	LIU X Y, WANG Z X, SUN Y, et al. ISA-KGC: integrated semantics-structure analysis in knowledge graph completion[J]. IEEE Access, 2024, 12: 57250-57260. DOI URL
[20]	BHANDIWAD D, GATTOGI P, KANGEN A, et al. Bridging language models and knowledge graphs with controlled natural languages[J]. Knowledge-Based Systems, 2026, 337: 115405. DOI URL
[21]	康月, 薛惠珍, 华斌. 面向深度学习网络的细粒度商品评价分析[J]. 计算机工程与应用, 2021, 57(11): 140-147. DOI
	KANG Y, XUE H Z, HUA B. Analysis of fine-grained commodity evaluation for deep learning network[J]. Computer Engineering and Applications, 2021, 57(11): 140-147 (in Chinese). DOI
[22]	CAO Z Y, LUO C. Link prediction for knowledge graphs based on extended relational graph attention networks[J]. Expert Systems with Applications, 2025, 259: 125260. DOI URL
[23]	ARTIME O, GRASSIA M, DE DOMENICO M, et al. Robustness and resilience of complex networks[J]. Nature Reviews Physics, 2024, 6(2): 114-131. DOI
[24]	AL MUSAWI A F, ROY S, GHOSH P. Examining indicators of complex network vulnerability across diverse attack scenarios[J]. Scientific Reports, 2023, 13(1): 18208. DOI
[25]	富坤, 魏昊宇, 刘伟静, 等. 拓扑语义双域协同的图神经网络框架[J]. 计算机应用, 2026, 46(5): 1378-1387. DOI
	FU K, WEI H Y, LIU W J, et al. Graph neural network framework for topology semantic dual-domain collaboration[J]. Journal of Computer Applications, 2026, 46(5): 1378-1387 (in Chinese). DOI
[26]	王静, 白文超, 杜冰. 中国经济韧性与生态韧性耦合协调及其空间关联网络结构[J]. 环境科学, 2026, 47(7): 4823-4835.
	WANG J, BAI W C, DU B. Coupling coordination and spatial correlation network structure of economic resilience and ecological resilience[J]. Environmental Science, 2026, 47(7): 4823-4835 (in Chinese).

典型治理情景	治理主体诉求			冲突链路
典型治理情景	政府	企业	社会	冲突链路
用水管理	考核与约束	成本与达标	公平与成效	考核要求提高→企业执行受压→节水效果受到质疑
生态修复	红线管控	修复投入	修复效果	修复任务推进→空间管控收紧→修复责任与效果争议显现
污染治理	制度监管	工程实施	信息公开	制度要求强化→工程治理推进→信息披露与社会监督跟进
防灾预警	平台运行	配套保障	获取信息	预警信息发布→响应措施落实→公众感知与反馈存在落差

典型治理情景	治理主体诉求			冲突链路
典型治理情景	政府	企业	社会	冲突链路
用水管理	考核与约束	成本与达标	公平与成效	考核要求提高→企业执行受压→节水效果受到质疑
生态修复	红线管控	修复投入	修复效果	修复任务推进→空间管控收紧→修复责任与效果争议显现
污染治理	制度监管	工程实施	信息公开	制度要求强化→工程治理推进→信息披露与社会监督跟进
防灾预警	平台运行	配套保障	获取信息	预警信息发布→响应措施落实→公众感知与反馈存在落差

语义标签	定义	实例	实例量
WRS	水资源统筹与节约利用	用水定额考核、节水效益评价	72
ECR	生态修复与国土保护	山水林田湖草沙一体化治理、生态保护红线监管	81
PFC	污染防治与清洁生产	VOCs治理工程、环境信息披露诉求	76
DRI	灾害防控与基础设施韧性	城市排涝系统建设、应急响应机制	71
GMC	协同治理机制	生态补偿政策、企业在线排放申报平台	102

语义标签	定义	实例	实例量
WRS	水资源统筹与节约利用	用水定额考核、节水效益评价	72
ECR	生态修复与国土保护	山水林田湖草沙一体化治理、生态保护红线监管	81
PFC	污染防治与清洁生产	VOCs治理工程、环境信息披露诉求	76
DRI	灾害防控与基础设施韧性	城市排涝系统建设、应急响应机制	71
GMC	协同治理机制	生态补偿政策、企业在线排放申报平台	102

实体标签	政府示例	社会示例	企业示例	总量
WRS	节水绩效评价	居民节水宣传活动	工业水平衡测试	21
ECR	生态保护红线监管	修复成果公示监督	绿色产业示范区	17
PFC	排污许可管理	公众举报通道	排放口在线监控	18
DRI	应急响应机制	黄河水情速报	—	7
GMC	生态补偿政策	公众听证会	在线申报平台	9