Data recommendation method and device, and storage medium

A system, comprising:

• a plurality of servers for a content provider, each server including processors and memory, the plurality of servers organized into three architectural layers that operate on three distinct time scales, including an offline layer, an intermediate layer, and a real-time layer, and the servers include a plurality of instructions stored in the memory of the plurality of servers that, when executed by the one or more processors of the servers, cause the one or more processors to perform the following operations:
• obtaining a periodic service attribute corresponding to a terminal identifier of a user terminal and a real-time service attribute corresponding to the terminal identifier,
• the periodic service attribute being a first label attribute relevant for content recommendation that corresponds to the terminal identifier and that is obtained through calculation according to a first type of service operations for content of the content provider that have been performed under the terminal identifier in a first preset period of time corresponding to an update cycle of the offline layer, and
• the real-time service attribute being a second label attribute relevant for content recommendation that corresponds to the terminal identifier and that is obtained through calculation according to a second type of service operations that for content of the content provider that have been performed under the terminal identifier in real time corresponding to a response time requirement of the real-time layer;
• selecting at least one piece of recommended content in a content data set of the content provider according to the periodic service attribute and the real-time service attribute, wherein selection is performed in the intermediate layer with a time scale between the update cycle of the offline layer and the response time requirement of the real-time layer, and corresponding selection processes are performed on an on-demand basis for a plurality of terminal identifiers corresponding to user terminals that are currently actively engaged in interaction with the real-time layer;
• and
• sending the at least one piece of recommended content to the user terminal as recommended content to the user of the user terminal.

A non-transitory computer-readable storage medium storing a plurality of instructions configured for execution by a plurality of servers each having one or more processors, wherein the plurality of servers provide services of a content provider, and are organized into three architectural layers that operate on three distinct time scales, including an offline layer, an intermediate layer, and a real-time layer, and the plurality of instructions cause the plurality of servers to perform the following operations:

• obtaining a periodic service attribute corresponding to a terminal identifier of a user terminal and a real-time service attribute corresponding to the terminal identifier,
• the periodic service attribute being a first label attribute relevant for content recommendation that corresponds to the terminal identifier and that is obtained through calculation according to a first type of service operations for content of the content provider that have been performed under the terminal identifier in a first preset period of time corresponding to an update cycle of the offline layer, and
• the real-time service attribute being a second label attribute relevant for content recommendation that corresponds to the terminal identifier and that is obtained through calculation according to a second type of service operations that for content of the content provider that have been performed under the terminal identifier in real time corresponding to a response time requirement of the real-time layer;
• selecting at least one piece of recommended content in a content data set of the content provider according to the periodic service attribute and the real-time service attribute, wherein selection is performed in the intermediate layer with a time scale between the update cycle of the offline layer and the response time requirement of the real-time layer, and corresponding selection processes are performed on an on-demand basis for a plurality of terminal identifiers corresponding to user terminals that are currently actively engaged in interaction with the real-time layer;
• and
• sending the at least one piece of recommended content to the user terminal as recommended content to the user of the user terminal.