The families, as a kind of the most common consumer units, have a considerable scale in the field of passenger transportation market. Ac-curately identifying family structures can help the carriers provide passengers with personalized travel services and product recommenda-tion. Studies the issue of finding family structures in passenger groups and proposes a kind of typed community discovery method based on relationship classification to determine family structures in passenger social networks. Experimental results on a real data set of passen-ger travel records in the field of passenger transport demonstrate that the method can effectively find family structures from historical trav-el records.
Passenger Social NetworksFamily StructuresRelationship ClassificationCommunity Detection
NETL
NSTL
万方数据
维普
