多语言大数据环境下的复杂网络行为分析、预测和干预

项目名称： 多语言大数据环境下的复杂网络行为分析、预测和干预

项目编号： No.U1435215

项目类型： 联合基金项目

立项/批准年度： 2015

项目学科： 自动化技术、计算机技术

项目作者： 吾守尔·斯拉木

作者单位： 新疆大学

项目金额： 200万元

中文摘要： 多语言环境下的社交关系、信息传播构成了内容丰富、规模巨大的复杂网络系统。研究针对其中异常行为的高效预测算法和干预理论，将为理解和控制复杂系统行为提供有效的支持。然而，这一复杂网络系统往往呈现出十分复杂的内部结构，使得对其行为进行分析，面临着大规模、多模态等大数据挑战。因此，分析、预测和干预多语言环境下的复杂网络行为，具有重大的理论价值和实际意义。. 本项目中，我们将从“多语言信息管理”、“复杂网络行为分析”，和“异常行为预测与干预”三个方面展开工作。首先，研究如何统一管理多语言信息数据，以实现信息的合理存储，并支持分析算法的高效执行；其次，研究如何利用大规模网络计算方法，分析多语言环境下复杂网络系统的行为特征和演化机理；最后，研究异常行为的建模、预测和干预理论，并设计高效算法，对其干预效果进行实验验证。

中文关键词： 大数据；复杂网络分析；多语言；行为预测；行为干预

英文摘要： The social ties and information exchange under the networking environment with multiple languages, forms the complex network system with rich content and huge volume. To study the efficient algorithms for predicting its abnormal behavior, and the theory of interruption, helps understanding and controlling the complex systems. However, this kind of complex network systems usually reveal extremely complicated structures inside, which bring the challenges of big data, like big volume and high variety, to the analysis. Hence, studying the methods for analyzing, predicting and interruptingthe behavior of complex network systems with multiple languages, is a valuable topic for theoretical research and practical exploration.. In this project, our work will focus on “management of information with multi-languages”, “behavior analysis of complex networks”, and “prediction and interruption of abnormal behaviors”. At first, we will study how to organize and manage the data containing information with multiple languages, in order to store them efficiently and support the algorithm execution with high performance; then, we will study the characters and evolution rules of the complex network behavior, by harnessing the complex network computing techniques for big data; at last, we will study the theory of prediction and interruption of the abnormal behavior, and design efficient algorithms to test the performance of the strategy of interruption.

英文关键词： big data;complex network analysis;multi-language;behavior prediction;behavior control