面向新一代调控系统的应用个性化推荐技术  

Personalized Application Recommendation Technology in New Generation Power Grid Dispatching and Control System

作　　者：邹庆 吴冠宇[1,2] 黄昆 余璟 高原[1,2,4] ZOU Qing;WU Guanyu;HUANG Kun;YU Jing;GAO Yuan(NARI Group Corporation(State Grid Electric Power Research Institute),Nanjing 211106;NARI Technology Co.,Ltd.,Nanjing 211106;State Grid Jiangsu Electric Power Company,Nanjing 210024;State Key Laboratory of Smart Grid Protection and Operation Control,Nanjing 211106)

机构地区：[1]南瑞集团有限公司(国网电力科学研究院有限公司),南京211106 [2]国电南瑞科技股份有限公司,南京211106 [3]国网江苏省电力公司,南京210024 [4]智能电网保护和运行控制国家重点实验室,南京211106

出　　处：《计算机与数字工程》2023年第2期423-427,共5页Computer & Digital Engineering

基　　金：国家电网公司科技项目“新一代电网调度控制系统微服务框架与基础关键技术研究与应用”资助。

摘　　要：新一代电网调度控制系统的目标是建设开放共享的系统生态,各厂家广泛参与,为用户提供各类场景数千个应用。为了帮助业务用户高效快捷的筛选出需要的应用,论文提出了一种面向新一代调控系统的个性化应用推荐技术,基于电网应用的关键词和应用分类属性,建立应用的专家标签多维特征模型,根据用户下载安装、卸载等历史行为反馈,分析用户对应用的兴趣偏好,结合相同专业用户的偏好特征,预测用户对其他应用的兴趣程度,从而为用户实现个性化应用推荐。通过试验表明,相对传统的、单一维度的、基于标签的推荐算法,论文算法加入多维特征标签,并基于同类用户协同推荐,提高了应用推荐的准确度,为用户实现了更高质量的个性化推荐。The new generation of power grid dispatching control system aims to build an open and shared system ecology,with extensive participation of various manufacturers,thousands of applications are provided in various scenarios.In order to help business users to efficiently and quickly filter out the required applications,this paper proposes a personalized application recommendation technology for a new generation of power grid control system.Based on the keywords and application classification attributes of power grid applications,a multi-dimensional feature model of expert tags for applications is established.According to user's historical behavior feedback such as downloading,installing and uninstalling,the user's interest preference for applications is analyzed,and the preference characteristics of the same professional users are combined to predict the user's interest in other applications,so as to realize personalized application recommendation for users.Experiments show that,compared with the traditional,single-dimensional,tag-based recommendation algorithm,the algorithm in this paper adds multi-dimensional signatures and recommends collaboratively based on similar users,which improves the accuracy of application recommendation and achieves higher-quality personalization for users recommend.

关 键 词：新一代电网调度控制系统 个性化应用推荐 专家标签 多维特征 用户协同 

分 类 号：V242.3[航空宇航科学与技术—飞行器设计]