Social media account filtering method and apparatus

A social media user account filtering apparatus, comprising:

• a processor and a memory, and the memory storing computer readable instructions, where in the processor, when executing the instructions, is configured to:
• parameterize a social activity network to obtain a parameter set comprising a user account set, a user activity set, a relationship set between user accounts, and a relationship set between user accounts and user activities;
• construct a hypergraph data structure of the social activity network comprising nodes and hyperedges according to the parameter set, wherein a node of the hypergraph comprises a user account of the user account set and a hyperedge comprises a set of user accounts that participate in an activity of the social activity network of an activity type or a friendship relation between one user account and another user account;
• obtain an activity type hyperedge set in the hypergraph (a first hyperedge set), a set consisting of all user accounts in a hyperedge except a particular user account (a reduced user account set), a hyperedge set corresponding to types of activities that the particular user account participates in (a second hyperedge set), a proportional influence of activities to the particular user account, and a friend set of the particular user account;
• obtain a proportional influence of friends to the particular user account according to the proportional influence of activities to the particular user account;
• obtain a transition probability of a node by performing a random walk in the hypergraph according to the proportional influence of friends to the particular user account, the friend set of the particular user account, the proportional influence of activities to the particular user account, the reduced user account set, and the second hyperedge set;
• and
• obtain a candidate node set and an influence of the candidate node set by:
• obtaining a total influence variable of an user account, estimating an influence value of the candidate node set according to the total influence variable of the user account, a transition probability between nodes in a remaining user account set obtained by subtracting the candidate node set from the user account set, and a transition probability from a node in the remaining user account set to a node in the candidate node set;
• and
• obtain the candidate node set having a maximum influence value through iteratively estimation, and using the candidate node set having the maximum influence value as a seed node set.

A social media user account filtering method performed by a processor in communication with a memory storing instructions, comprising:

• obtaining user accounts of a social activity network and user activity information;
• constructing a hypergraph of the social activity network comprising nodes and hyperedges according to the user accounts and the user activity information, wherein a node in the hypergraph comprises the user account in the social activity network, and a hyperedge in the hypergraph comprises a set of user accounts that participates in a user activity of an activity type, or a friendship relation between one user account and another user account;
• for each node in the hypergraph, calculating a probability that another node of the hypergraph would walk to the node when performing a random walk along the hyperedge in the hypergraph, and obtaining an influence value of the node in the social activity network according to the probability;
• and
• sequentially filtering nodes of the hypergraph to obtain a sequence of nodes having a maximum influence by using an iteration algorithm, to form a seed node set.