大数据分析在国际石油贸易领域的应用现状与发展趋势

doi:10.3969/j.issn.1002-302x.2018.03.007

摘要/Abstract

摘要： 近年来大数据分析技术方兴未艾，“互联网+”成为传统油气行业转型升级、融合创新的重要途径。国际石油贸易领域信息化应用先后经历了桌面客户端程序+ 中央数据库的传统数据库时代、网页版客户端+ 分布式数据库时代两个阶段，正在步入人工智能+ 大数据+ 物联网的“互联网+”的第三阶段。在第三阶段，业内希望通过大数据分析技术继续提高内部的执行效率和风险控制预警能力，改变以往对外部数据的碎片化获取和共享方式，深度挖掘和整合不可量化的内外部信息，应用人工智能算法进行经营决策的优化，为一线交易员提供交易辅助决策。基于人工智能平台的辅助交易决策平台、大数据信用风险评估及预警平台、标准化报告智能分析及合同解析，均将成为第三阶段的典型应用场景。

关键词: 大数据分析, 人工智能, 国际石油贸易, 互联网+, ETRM 系统

Abstract: Big data analysis technology has been flourishing in recent years. “Internet+” has become the important way for traditional oil and gas enterprises to modernize and integrate themselves for industrial conversion and innovation. Application of information in the international petroleum trade area has experienced two stages -- the era of desktop client program + traditional database of central database and the era of web page client + distributed database. It now enters the third stage -- artificial intelligence + big data + “Internet +” Internet of Things. Under the third stage, the insiders hoped that big data analysis technology could continue to improve the internal execution efficiency and the risk control early-warning capacity, changing the fragmentation acquisition and sharing mode of external information and deeply tapping and integrating the non-quantifiable internal and external information. Artificial intelligent algorithms are used to optimize the business policies and provide the traders with decision-making assistance. The assistant trading decision-making platform based on artificial intelligence, the big data credit risk assessment and early-warning platform and standard report of intelligent analysis and contract analysis will become the typical application situations for the third stage.

中图分类号:

郑兴扬　张　彤　刘昊伟. 大数据分析在国际石油贸易领域的应用现状与发展趋势[J]. 石油科技论坛, 2018, 37(3): 41-46.

Zheng Xingyang, Zhang Tong, Liu Haowei. Present Conditions and Development Trend for Big Data Analysis Used in International Petroleum Trade Area[J]. Petroleum Science and Technology Forum, 2018, 37(3): 41-46.

参考文献

[1] 祝叶华. 2016 年热点科技事件回眸[J]. 科技导报, 2017, 35(1): 136-148. Zhu Yehua. Ten hot events of science and technology in 2016[J]. Science & Technology Review,2017,35(1): 136-148.br/> [2] 李宇静, 陈庆俊, 赵云峰. 我国石化工业优化发展趋势[J]. 石油科技论坛, 2017, 36(2):1-7.Li Yujing, Chen Qingjun, Zhao Yunfeng. Optimization and development trend of China’s petrochemical insustry[J]. Oil Forum, 2017,36(2):1-7.br/> [3] 覃伟中. 积极推进智能制造是传统石化企业提质增效转型升级的有效途径[J]. 当代石油石化, 2016, 24(6): 1-4. Qin Weizhong. Intelligent process manufacturing-an efficient way to upgrade traditional refineries[J]. Petroleum & Petrochemical Today, 2016, 24(6): 1-4.br/> [4] 李伟, 张艺.ETRM 系统简介[J]. 电子技术与软件工程, 2013,22(11):25-25. Li Wei, Zhang Yi. Brief introduction of ETRM system[J]. Electronic Technology & Software Engineering,2013,22(11):25-25.br/> [5] 郑兴扬, 张彤. 国际石油贸易实用攻略[M]. 北京: 石油工业出版社,2014. Zheng Xingyang, Zhang Tong. Applicable strategy for international petroleum trade[M].Beijing: Petroleum Industry Press,2014.br/> [6] 吴晓求. 证券投资学[M]. 北京: 中国人民大学出版社, 2004. Wu Xiaoqiu. Securities investment principles[M].Beijing: China Renmin University Press,2004.br/> [7] 李海阔, 曾小杰. 基于期货市场的资金流向模型及量化交易策略[J]. 科学咨询,2008, 9(1):57-58. Li Haikuo, Zeng Xiaojie. Fund flow model and quantified trade policies[J]. Policy & Scientific Consult,2008,9(1):57-58.br/> [8] 王宣承. 基于LASSO 和神经网络的量化交易智能系统构建——以沪深300股指期货为例[J]. 投资研究,2014, 33(9):23-39. Wang Xuancheng.Construct intelligent quantitative trading systems based on Lasso and Anns-A case study of CSI300 futures [J]. Review of Investment Studies, 2014, 33(9):23-39.br/> [9] 程广明. 大数据治理模型与治理成熟度评估研究[J]. 科技与创新,2016,3(9):6-7. Cheng Guangming. Research on big data handling model and handling maturity assessment[J].Science and Technology & Innovation,2016,3(9):6-7.br/> [10] 吴韶鸿. 大数据开源技术发展研究[J]. 现代电信科技, 2014, 44(8):17-22. Wu Shaohong. Study of big data sources technological development[J].Modern Science & Technology of Telecommunicatio,2014,44( 8):17-22.br/> [11] 李晓慧, 孙蔓莉. 业绩归因分析在审计风险识别中的运用研究[J]. 会计研究,2012,33(9):82-88. Li Xiao hui, Su Ma nli Applica tion o f perf ormance attribution analysis in recognition of auditing risks [J]. Accounting Research,2012,33(9):82-88.br/> [12] 霍四通.NLP 中语义语法的构造及其应用[J]. 语言研究集刊, 2005:173-193,402. Huo Sitong. Semantic and grammatical structure of NLP and its application[J]. Collection of Linguistic Study Papers, 2005:173-193,402.br/> [13] 沈沛龙, 任若恩. 现代信用风险管理模型和方法的比较研究[J]. 经济科学,2002,24(3):32-41. Shen Peilong, Ren Ruoen. Comparative research on modern credit risks management model and methods[J]. Economic Science,2002,24(3):32-41.br/> [14] 刘堃, 巴曙松, 任亮. 中国信用风险预警模型及实证研究——基于企业关联关系和信贷行为的视角[J]. 财经研究,2009, 35(7): 14-28. Liu Kun, Ba Shusong, Ren Liang. Research on China credit risks early-warning model -- From angle of enterprises’ correlations and credit behavior[J]. Journal of Finance and Economics, 2009, 35(7): 14-28.br/> [15] 赵蓉英, 许丽敏. 文献计量学发展演进与研究前沿的知识图谱探析[J]. 中国图书馆学报,2010,54(5):60-68. Zhao Rongying, Xu Limin. Development and evolution of literature measurement and knowledge diagram analysis of frontier study[J].Journal of Library Science in China, 2010,54(5):60-68.br/> [16] 马海兵, 刘永丹, 王兰成, 等. 三种文档语义倾向性识别方法的分析与比较[J]. 现代图书情报技术, 2007,27(4):43-47. Ma Haibing, Liu Yongdan, Wang Lancheng, et al. An analysis and comparison of three methods for document semantic orientation recognition[J]. New Technology of Library and Information Service,2007,27(4):43-47.