Social network-based automated program channel recommender

A recommendation system comprising:

• one or more communication interfaces;
• one or more memories that store instructions;
• and
• one or more processors to execute the instructions to:
• obtain, via at least one of the one or more communication interfaces, program historical data associated with users that receive one or more programs via one or more channels;
• obtain, via at least one of the one or more communication interfaces, social network data associated with the users;
• calculate based on the social network data, a social similarity value that indicates a social similarity between one of the users and other users;
• calculate based on the program historical data, a channel-interest similarity value that indicates a common interest between the one of the users and the other users in relation to the one or more channels used by the users to receive the one or more programs;
• calculate based on the social similarity value and the channel-interest similarity value, a similarity index value that indicates a similarity between the one of the user and the other users;
• calculate based on the program historical data a program regularity value, for each program, that indicates a regularity of consumption of each program over a time period;
• calculate based on the program regularity value, a program weight value, for each program, that indicates a priority value;
• calculate based on the program historical data, a stay-time, for each channel, that indicates a time period each of the users remained on each channel;
• calculate based on each program weight value, each stay-time, and each similarity index value, a channel weight for each channel;
• and
• select based on each channel weight, one or more channels to recommend to at least one of the users.

A non-transitory storage medium storing instructions executable by a computational device, wherein the instructions comprise instructions to:

• obtain program historical data associated with users that receive one or more programs via one or more channels;
• obtain social network data associated with the users;
• calculate based on the social network data, a social similarity value that indicates a social similarity between one of the users and other users;
• calculate based on the program historical data, a channel-interest similarity value that indicates a common interest between the one of the users and the other users in relation to the one or more channels used by the users to receive the one or more programs;
• calculate based on the social similarity value and the channel-interest similarity value, a similarity index value that indicates a similarity between the one of the user and the other users;
• calculate based on the program historical data a program regularity value, for each program, that indicates a regularity of consumption of each program over a time period;
• calculate based on the program regularity value, a program weight value, for each program, that indicates a priority value;
• calculate based on the program historical data, a stay-time, for each channel, that indicates a time period each of the users remained on each channel;
• calculate based on each program weight value, each stay-time, and each similarity index value, a channel weight for each channel;
• and
• select based on each channel weight, one or more channels to recommend to at least one of the users.