Microsoft Technology Licensing, LLC

Yulia Astakhova

Jeffrey Gee

Deepak Kumar

Mahesh Subhash Joshi

Gungor Polatkan

Theodore H Hwa

Shivani Rao

Lifeng Sang

Konstantin Salomatin

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&#x2014;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.

Ranking carousels of on-line recommendations of videos

Computerized methods enable automatic monitoring of requests to an online service and apply access restrictions, as appropriate, to servicing of requests in real-time or near real-time. For each request received by the online service, a plurality of parameters associated with the request are identified, and counters corresponding to the particular values of the plurality of parameters associated with the request are incremented to track the number of times a parameter value appears or occurs in connection with requests to the online service. A first level check or analysis is performed to determine whether a second level check or analysis is required. The first level check or analysis comprises an initial screening that is not computationally intensive. The second level check or analysis is more resource-intensive and is triggered depending on the outcome of the first level check or analysis.

Analyzing requests to an online service

Growing community of inventors

Oakland, CA, United States of America

Yulia Astakhova