融合多源数据的科研人员画像构建方法研究

Study for the Construction Method of Scientist Profile with Multi-Source Data Fusion

[目的／意义]大数据时代需要将“人”数据化，科研人员也需要数据化。科研人员画像的建立，对于科研管理层全面了解科研人员的信息、客观评价其研究水平等有重要作用，可以作为分析科研人员研究行为或专家推荐的基础，提高科研管理效率。[方法／过程]首先提出科研人员画像的概念，认为其是描述科研人员信息的标签的集合。其次，以个人主页、知网、基金网等多个异构数据源的数据为基础，提出融合多源数据的科研人员画像构建方法，分别从科研人员的基础属性、科研偏好和科研关系三方面形式化描述了科研人员信息，并提取各个维度的标签，以可视化的方式展示其画像。最后，分别以国内外两位科研人员为例，说明了科研人员画像构建方法的可行性。[结果／结论]科研人员画像的构建适用于国内外的科研人员，能够全面描述科研人员信息并直观展示出来。

[Purpose/significance] In the age of big data, people need to be digitized, and researchers need to digi- tize them. The establishment of scientists profile is of great importance for scientific research managers to comprehensively understand the information of researchers and objectively evaluate their research level. It can be used as the basis for analyzing the research behavior or recommendation of experts, and improving the efficiency of scientific research management. [Method/process] First of all, the concept of scientists profile is proposed, which is a collection of labels describing the information of scientific researchers. Secondly, based on the data of multiple heterogeneous data sources, such as personal homepage, knowledge network and fund network, this paper proposes a method for the construction of scientists profile with multi-source data. This method formally describes the information of scientific researchers from the three aspects of the basic attribute, scientific research preference and scientific research relationship, and extracts the labels of each dimension to vividly display the profile in a visual way. Finally, the feasibility of this method is illustrated by taking two researchers at home and abroad as examples. [Result/conclusion] The construction of the scientists profile is suitable for researchers at home and abroad, which can fully describe the information of researchers and show them visually.