基于社会感知的电力服务渠道网点推荐系统
|
摘要
随着泛在地理信息、大数据和移动互联网、物联网等技术在服务行业的迅速发展,电力行业的服务也迫切需要进行转型和升级。提出了一种基于社会感知计算的营销渠道服务网点的智能化推荐框架和模型,并基于多种大数据技术开发了电力服务渠道网点推荐系统。首先探讨客户网点推荐、传感设施、客户行为模式和推理预测模型之间的相互作用机理,形成客户网点选择行为的社会感知计算概念模型;其次,结合回归和预测技术,提出基于人工智能的社会感知推理计算;最后,基于HDFS,Spark及空间大数据等计算机前沿技术设计实现了原型系统。为电网客户网点服务推荐提供新的思路和借鉴。
With the development of various technologies in service industry, such as ubiquitous geographic information, big data,mobile Internet, and Internet of things, power enterprises are also urgently needed to be upgraded. The paper proposes the intelligent recommendation framework and the model of marketing channel service network based on social perception computation, and implements the recommendation system based on a variety of big data techniques. Firstly,the interaction mechanism is discussed among customer network recommendation, sensing facilities, customer behavior pattern and reasoning prediction model, and a conceptual model is established for calculating the social perception of the customer network selection behavior. Secondly, combined with the classical regression and prediction techniques in artificial intelligence, the social perception reasoning calculation based on artificial intelligence is proposed. Finally,the prototype system is developed and realized based on HDFS, Spark and spatial big data,and a new way of thinking and reference for the service recommendation of the power grid users is provided.
With the development of various technologies in service industry, such as ubiquitous geographic information, big data,mobile Internet, and Internet of things, power enterprises are also urgently needed to be upgraded. The paper proposes the intelligent recommendation framework and the model of marketing channel service network based on social perception computation, and implements the recommendation system based on a variety of big data techniques. Firstly,the interaction mechanism is discussed among customer network recommendation, sensing facilities, customer behavior pattern and reasoning prediction model, and a conceptual model is established for calculating the social perception of the customer network selection behavior. Secondly, combined with the classical regression and prediction techniques in artificial intelligence, the social perception reasoning calculation based on artificial intelligence is proposed. Finally,the prototype system is developed and realized based on HDFS, Spark and spatial big data,and a new way of thinking and reference for the service recommendation of the power grid users is provided.
引文
[1]周辛南,孙志杰,谢枫,等.面向营配信息贯通的业扩报装系统设计与实现[J].智慧电力,2018,46(8):89-93.ZHOU Xinnan, Sun zhijie, Xie feng, et al. Design of business expansion reporting system based on marketing and distribution in integration&its realization[J]. Smart Power, 2018,46(8):89-93.
[2] LIU Y, LIU X, GAO S, et al. Social sensing:a new approach to understanding our socioeconomic environments[J]. Annals of the Association of American Geographers,2015, 105(3):512-530.
[3] GOODCHILD M. Citizens as sensors:the world of volunteered geography[J]. Geo Journal, 2007, 69(4):211-221.
[4] BRUNSDON C, FOTHERINGHAM S, CHARLTON M.Geographically weighted regression:a method for exploring spatial nonstationarity[J]. Geographical Analysis,1996, 28(4):281-298.
[5] BRUNSDON C, FOTHERINGHAM S, CHARLTON M. Geographically weighted regression-modelling spatial nonstationarity[J]. Journal of the Royal Statistical Society,1998, 47(3):431-443.
[6]吴森森.地理时空神经网络加权回归理论与方法研究[D].杭州:浙江大学,2018.
[7]田廓,田消冰,段来越,等.国网陕西电力“四链五率”投资进度精益化管控体系建设及Tableau平台开发应用[J].智慧电力,2018,46(3):74-79+86.TIAN Kuo, TIAN Xiaobing, DU AN Laiyue, et al. Four-chain and five-rate based investment progress lean management system establishment and tableau platform application development in state grid shaaxi electic power company[J]. Smart Power, 2018,46(3):74-79+86.
[8]武文广,王朝亮,叶方彬,等.用电信息釆集系统多业务高效协同处理关键技术[J].智慧电力,2017,45(11):78-84.WU Wenguang, WANG Chaoliang, YE Fangbin, et al.Key technologies in high efficiency coprocessing of multiservice for power consumption information acquisition system[J]. Smart Power, 2017,45(11):78-84.
[9] MOTEVALLI A, POURGHASEMI H R, ZABIHI M.2.12-Assessment of GIS-based machine learning algorithms for spatial modeling of landslide susceptibility;Case study in iran A2-huang, BO[M]. Oxford:Comprehensive Geographic Information Systems. 2018,258-280.
[10] MOJADDADI H, PRADHAN B, NAMPAK H, et al. Ensemble machine-learning-based geospatial approach for flood risk assessment using multi-sensor remote-sensing data and GIS[J]. Geomatics, Natural Hazards and Risk,2017, 8(2):1080-1102.
[11] DUANNAN Y, GUANGZHI Z. Application of support vector machine in prediction of reservoir parameters[C]. Bangalore:Proceedings of the IEEE 10th International Conference on Signal Processing Proceedings, 24-28 Oct. 2010
[12] CHEN W, POURGHASEMI H R, KORNEJADY A, et al. Landslide spatial modeling:introducing new ensembles of ann, maxent, and svm machine learning techniques[J].Geoderma, 2017, 305(Supplement C):314-327.
[13]傅贵,韩国强,逯峰,等.基于支持向量机回归的短时交通流预测模型[J].华南理工大学学报(自然科学版),2013,41(9):71-76.FU Gui, HAN Guoqiang, LU Feng, et al. Short-term traffic flow forecasting model based on support vector machine regression[J]. Journal of South China University of Technology(Natural Science Edition), 2013, 41(9):71-76.
[14] ZHENG Y, LIU L, WANG L, et al. Learning transportation mode from raw gps data for geographic applications on the web[C]. Beijing:Proceedings of the International Conference on World Wide Web, 2008.
[15]刘昆生.支持移动终端的广告投放平台的设计与实现[D].杭州:浙江工业大学,2017.
[16]刘益腾.面向服务思想和私有云平台的电力大数据架构设计与实现[D].成都:电子科技大学,2018.
[17]刘东岳.基于Spark的数据挖掘方法在电网数据分析中的应用研究[D].北京:北京邮电大学,2018.
[2] LIU Y, LIU X, GAO S, et al. Social sensing:a new approach to understanding our socioeconomic environments[J]. Annals of the Association of American Geographers,2015, 105(3):512-530.
[3] GOODCHILD M. Citizens as sensors:the world of volunteered geography[J]. Geo Journal, 2007, 69(4):211-221.
[4] BRUNSDON C, FOTHERINGHAM S, CHARLTON M.Geographically weighted regression:a method for exploring spatial nonstationarity[J]. Geographical Analysis,1996, 28(4):281-298.
[5] BRUNSDON C, FOTHERINGHAM S, CHARLTON M. Geographically weighted regression-modelling spatial nonstationarity[J]. Journal of the Royal Statistical Society,1998, 47(3):431-443.
[6]吴森森.地理时空神经网络加权回归理论与方法研究[D].杭州:浙江大学,2018.
[7]田廓,田消冰,段来越,等.国网陕西电力“四链五率”投资进度精益化管控体系建设及Tableau平台开发应用[J].智慧电力,2018,46(3):74-79+86.TIAN Kuo, TIAN Xiaobing, DU AN Laiyue, et al. Four-chain and five-rate based investment progress lean management system establishment and tableau platform application development in state grid shaaxi electic power company[J]. Smart Power, 2018,46(3):74-79+86.
[8]武文广,王朝亮,叶方彬,等.用电信息釆集系统多业务高效协同处理关键技术[J].智慧电力,2017,45(11):78-84.WU Wenguang, WANG Chaoliang, YE Fangbin, et al.Key technologies in high efficiency coprocessing of multiservice for power consumption information acquisition system[J]. Smart Power, 2017,45(11):78-84.
[9] MOTEVALLI A, POURGHASEMI H R, ZABIHI M.2.12-Assessment of GIS-based machine learning algorithms for spatial modeling of landslide susceptibility;Case study in iran A2-huang, BO[M]. Oxford:Comprehensive Geographic Information Systems. 2018,258-280.
[10] MOJADDADI H, PRADHAN B, NAMPAK H, et al. Ensemble machine-learning-based geospatial approach for flood risk assessment using multi-sensor remote-sensing data and GIS[J]. Geomatics, Natural Hazards and Risk,2017, 8(2):1080-1102.
[11] DUANNAN Y, GUANGZHI Z. Application of support vector machine in prediction of reservoir parameters[C]. Bangalore:Proceedings of the IEEE 10th International Conference on Signal Processing Proceedings, 24-28 Oct. 2010
[12] CHEN W, POURGHASEMI H R, KORNEJADY A, et al. Landslide spatial modeling:introducing new ensembles of ann, maxent, and svm machine learning techniques[J].Geoderma, 2017, 305(Supplement C):314-327.
[13]傅贵,韩国强,逯峰,等.基于支持向量机回归的短时交通流预测模型[J].华南理工大学学报(自然科学版),2013,41(9):71-76.FU Gui, HAN Guoqiang, LU Feng, et al. Short-term traffic flow forecasting model based on support vector machine regression[J]. Journal of South China University of Technology(Natural Science Edition), 2013, 41(9):71-76.
[14] ZHENG Y, LIU L, WANG L, et al. Learning transportation mode from raw gps data for geographic applications on the web[C]. Beijing:Proceedings of the International Conference on World Wide Web, 2008.
[15]刘昆生.支持移动终端的广告投放平台的设计与实现[D].杭州:浙江工业大学,2017.
[16]刘益腾.面向服务思想和私有云平台的电力大数据架构设计与实现[D].成都:电子科技大学,2018.
[17]刘东岳.基于Spark的数据挖掘方法在电网数据分析中的应用研究[D].北京:北京邮电大学,2018.