Combined collaborative filtering IPTV program recommendation method

The invention provides a combined collaborative filtering IPTV program recommendation method. A user-program scoring matrix is constructed for a program firstly; then filling is performed on the original user-program scoring matrix by means of item-based collaborative filtering; then the filed user-program scoring matrix acts as input of a singular value decomposition technology, and refilling can be performed on the original user-program scoring matrix by the singular value decomposition technology so that a user-program scoring matrix without missing value is obtained; and finally scores of items which are not scored in the original matrix are predicted by using the item-based collaborative filtering method on the user-program scoring matrix without missing value, and N programs with the highest prediction scores act as recommendation results of collaborative filtering.