Abstract: This application describes a data processing method, a server, and a computer storage medium. In a method, a real-time data stream is collected. The real-time data stream includes a plurality of usage data for a plurality of content. Each of the plurality of usage data is associated with (i) content identification information of a respective one of the plurality of content and (ii) a time stamp of the respective usage data and indicating one of a plurality of user actions that is performed on the respective one of the plurality of content. Further, each of the plurality of user actions is associated with an action weight. A user status queue is generated according to the plurality of usage data and the associated content identification information. A user status feature is determined. Recommended information is determined according to the user status feature and is sent to a user terminal.

Abstract: This application describes a data processing method, a server, and a computer storage medium. In the method, a real-time data stream is collected. The real-time data stream includes a first-type data representing a plurality of behaviors of a user and a second-type data representing information of interest to the user. A user status queue is generated according to the first-type data and the second-type data. User status changes are tracked in real time according to the user status queue and time information that indicates when the first-type data is generated by the user performing at least an action relating to the second-type data to determine a user status feature to determine a user status feature. Recommended information is determined according to the user status feature, and the recommended information is sent to a user terminal.