Abstract: A method including acquiring to-be-processed information corresponding to a real-time video application, the to-be-processed information comprising at least one of the following: customer identity information and real-time video identification information; identifying a target object and an information intent corresponding to the to-be-processed information; determining, according to the target object and the information intent, at least one response corresponding to the to-be-processed information; and sending the at least one response to a send terminal corresponding to the customer identity information.

Abstract: Disclosed is a method for supporting online services in providing content items to users of an online system. A request for loading a webpage of an online system is received from a client device. A plurality of content items eligible for being presented to the user is received. For each of the received content items, a trained model is identified based on characteristics of the content item, and a score is determined using the identified trained model and based on characteristics of the user. One or more content items is selected based on the determined scores. The selected one or more content items are sent to the client device for presentation to the user.