A Review of the Multi-source Data Feature-level Fusion Method in the Field of Library and Information Science
[Purpose/Significance]Multi-source data feature-level fusion is a method devised for the extraction and integration of multi-level features from diverse and multidimensional data sources,which is used to reveal the intrinsic correlations and complementarities of the data.This provides a more comprehensive and precise analytical perspective.The review of relevant research is of great significance to enrich research methods and promote the intelligent process of information science research.[Method/Process]On the basis of elaborating the importance and necessity of feature-level fusion research,this paper compiled the research results of feature-level fusion meth-ods in the field of library and information science in the past 10 years.[Result/Conclusion]At present,the multi-source data feature-level fusion methods used in the field of library and information science can be summarized into three categories:linear weighted fusion methods,feature-coupled fusion methods and neural network model based fusion methods.It demonstrates the applicable scenarios of various feature-level fusion methods and analyzes the problems exposed in the use of these methods in the field of library and information science,and prospects its future development in the academic environment.
feature-level fusionmulti-source data fusionmulti-source dataresearch review
NETL
NSTL
万方数据
