With the rapid development of information technology and network technology, the Internet is becoming more intelligent, personalized, and social, influencing and changing people's way of life. Many heterogeneous networks (mobile network, Internet, Television broadcasting network, etc.) and technology are integrated into an open communication network, that is, the integrated network. In the context of network integration, a large number of services, provided by service providers, have sprung to meet various needs of service consumers or users. Service is becoming a "collective term" that is also known as "everything as a service." Various services, including online shopping, music download, live streaming video, social networking, and various mobile apps, improve the efficiency of people's work and facilitate people's life. The ubiquitous and openness characters of the integrated network provide users with personalized services better. However, along with the explosion of services in the integrated network, there have emerged new problems. On the one hand, to the user, with the rapid growth of the type and number of services, the users run into the trouble of information overload, and usually users need to spend a lot of time finding themselves services they need; on the other hand, to the service provider, the process that users browse a large number of irrelevant services will no doubt make consumers submerged in the problem of information overload in the continuous loss. How to achieve fast and reliable selection and recommendation of optimal services for users in integrated network environment has become one of the most challenging issues in the field of service computing [1]. One of the most typical examples is social networking services. Because social networking service always has a huge user groups and users frequently update status, causing social networking services would produce lots of users and redundant