Matrix-based multi-granulation fusion approach for dynamic updating of knowledge in multi-source information

Multisource information fusion is an important big data technology that plays a crucial role in the fields of data mining and knowledge discovery. Multigranulation information fusion is an effective technique for obtaining critical information from multisource data. However, obtaining meaningful information from a dynamic multisource information system using a multigranulation fusion strategy has rarely been researched. Therefore, this study explores a matrix-based dynamic updating strategy for multigranulation fusion operators. First, a matrix-based method for computing multigranular fusion operators is proposed. Second, the matrix-based dynamic updating mechanism of the multigranularity fusion operator is discussed and constructed for four cases (deleting objects, adding objects, deleting sources, and adding sources). Finally, four groups of dynamic algorithms and static methods are compared to verify the effectiveness of the dynamic algorithm. The experimental findings show that the matrix-dynamic updating multigranulation fusion operator approach is effective and efficient.