| Summary: | To solve the problem of serious information overload caused by the explosive growth of Internet information, a time-weighted network structure recommendation algorithm is proposed by studying the traditional recommendation algorithm. This algorithm creates a "User-object-tag" tripartite graph and uses the mass diffusion algorithm to calculate the resource vectors obtained of the project. Then, according to the time attenuation problem, we design the time-weighted function based on user social tags. Finally, a new network structure recommendation algorithm is proposed by combining the time-weighted function with the tripartite graph recommendation algorithm. the experimental results demonstrate that the recommendation algorithm can solve the problem of dynamic migration about user interests and significantly improve accuracy of recommendation effectively.
|
|---|
