作者: Zhiyong Shen , Wei Hu , Qing Wang
DOI:
关键词:
摘要: A method and apparatus for predicting based on multi-source heterogeneous data. The comprises: acquiring, with regard to an event of a set type, at least two types historical data that can reflect result; establishing joint likelihood model attribute the type data; determining optimal estimation according maximum posterior principle; determining, probability distribution associated in model, parameter as prediction result predicted type. Some embodiments use hierarchical introduce different sources into layers, unify perform analysis, obtain more accurate, instant stable through effective fusion.