Abstract: The present disclosure relates to a system and a method for stream distribution. The method includes: determining a first parameter of a distributor to be higher or lower than a first threshold; determining a first viewer to have a second parameter higher than a second threshold with respect to streams recommended to the first viewer; determining a second viewer to have a second parameter lower than the second threshold with respect to streams recommended to the second viewer; and recommending a stream of the distributor to the first viewer or the second viewer according to a result of the determining the first parameter to be higher or lower than the first threshold.

Abstract: The present application relates to a system and method for highlight detection, and includes a highlight detection method for detecting highlights of a stream. The method comprises: collecting purchasing information from a user terminal; and detecting the highlight of the stream according to the purchasing information. The purchasing information includes purchasing actions of the user terminal, and the purchasing actions are actions related to purchase of the user terminal. According to the subject application, the highlights may be detected, captured and generated automatically, and the time and efforts for manual work may be saved.

Abstract: The present disclosure relates to a system, a method and a computer-readable tangible non-transitory medium for recommending live streaming data. The method includes identifying a set of live streaming programs according to an attribute of the user and a tag of each live streaming program in the set of live streaming programs, generating a first subset of live streaming programs from the set of live streaming programs according to a first criterion, and generating a second subset of live streaming programs from the set of live streaming programs according to a second criterion. The first criterion is different from the second criterion. The present disclosure can recommend contents in a more efficient way and increase user engagements.

Abstract: The present disclosure relates to a system, a method and a computer-readable medium for recommendation. The method includes obtaining viewer interaction data of a plurality of content types; determining distance values between different content types according to the viewer interaction data; determining a first viewer and a second viewer to have viewed a same content type; determining a distance value between a first content type viewed by the first viewer and a second content type viewed by the second viewer according to the distance values; and determining whether or not to recommend a stream corresponding to the first content type to the second viewer according to the distance value.

Abstract: The present application relates to a system and method for highlight detection, and includes a highlight detection method for detecting highlights of a stream. The method comprises: collecting purchasing information from a user terminal; and detecting the highlight of the stream according to the purchasing information. The purchasing information includes purchasing actions of the user terminal, and the purchasing actions are actions related to purchase of the user terminal. According to the subject application, the highlights may be detected, captured and generated automatically, and the time and efforts for manual work may be saved.