US 2020/0007937 A1 · RANKING CAROUSELS OF ON-LINE RECOMMENDATIONS OF VIDEOS

Abstract

The recommendation system provided with an on-line connection system identifies on-line recommendations of videos and generates a user interface (UI) by including into the resulting presentation selected recommendations of videos. The recommendations of videos presented in the UI are organized into groups that are topically coherent, where each group is decorated with a context annotation—an explanation of why the recommendations in a given carousel are relevant for a member. Each video that is being evaluated by the recommendation system with respect to a subject member profile is assigned an annotation that is selected from a plurality of potentially applicable annotations. The technical problem of optimizing an order of presentation of recommendations grouped by context annotations, in a UI where annotations drive the layout, is addressed by deriving ranks for different context annotations based on global and personalized click through rates and using these values assigned to respective context annotations in constructing the UI.

Claims20

Dependent claims

A computer implemented method comprising:

determining a set of context annotations associated with recommended videos selected for a subject member profile representing a member in an on-line connection system;
for each annotation from the set of context annotations, calculating a combined popularity score as a combination of a global popularity score and a personalized popularity score, the global popularity score derived using a click through rate (CTR) for groups of recommendations associated with the respective annotations for a set of member profiles representing members in the on-line connection system, the personalized popularity score derived using a CTR for groups of recommendations associated with the respective annotations for the subject member profile;
using at least one processor, determining an order of presentation of carousels based on respective combined popularity scores generated for annotations from the set of context annotations, each carousel having frames representing a subset of the recommended videos identified as associated with a particular annotation from the set of context annotations;
and
generating a presentation user interface (UI) by including the carousels into the UI in the determined order.

2 more elements

A system comprising:

one or more processors;
and
a non-transitory computer readable storage medium comprising instructions that when executed by the one or processors cause the one or more processors to perform operations comprising:
determining a set of context annotations associated with recommended videos selected for a subject member profile representing a member in an on-line connection system;
for each annotation from the set of context annotations, calculating a combined popularity score as a combination of a global popularity score and a personalized popularity score, the global popularity score derived using a click through rate (CTR) for groups of recommendations associated with the respective annotations for a set of member profiles representing members in the on-line connection system, the personalized popularity score derived using a CTR for groups of recommendations associated with the respective annotations for the subject member profile;
determining an order of presentation of carousels based on respective combined popularity scores generated for annotations from the set of context annotations, each carousel having frames representing a subset of the recommended videos identified as associated with a particular annotation from the set of context annotations;
and
generating a presentation user interface (UI) by including the carousels into the UI in the determined order.

5 more elements

Dependencies are inferred from the claim text.

Ranking carousels of on-line recommendations of videos

Life of this patent

Ranking carousels of on-line recommendations of videos

Life of this patent

Abstract

Claims20