Microsoft Technology Licensing, LLC

Linkedin Corporation

Alexandre Lee

Yan Liu

Shipeng Yu

Rahul Agarwal

Joseph Adler

John Reilly

Russell Melick

James Tac Lau

Jesse Bellister

This disclosure relates to systems and methods for searching names using name clusters. A method includes training a supervised machine learning system to learn a connection strength between a member and peers of the member; clustering the member with the peers in response to a threshold number of profile similarities between the member and the peers and the connection strength between the member and the peers being above a connection strength threshold value; and applying an unsupervised machine learning system using output from the supervised machine learning system and the clustering to generate a connection between the member and at least one of the peers.

Network estimation

Systems and methods for ranking search results based on members' posting activity and content are disclosed. The social networking system receives a search request for at least one member profile and retrieves member profiles in response to the search request. For a member profile in the member profiles, the social networking system identifies at least one submitted content item associated with the member profile and analyzes the at least one submitted content item to determine topics associated with the at least one submitted content item. The social networking system generates a topic similarity score for the member profile based on a comparison of the topics and a topic of interest associated with the search request. The social networking system ranks the member profiles based on generated topic similarity scores. The social networking system selects at least one member profile based on the member profile ranking.

Ranking search results based on members? posting activity and content

A content delivery system coupled to a computer network can provide large volumes of content to large numbers of recipients. The content is collected into digests and individual articles to be sent in email via an email channel established by the content delivery system to the recipients through the computer network. Content producers submit content for aggregation into various email deliveries and submit initial scheduling information. The scheduling information may specify target characteristics of preferred recipients of the content as well as general and initial scheduling preferences for email delivery. The content delivery system utilizes the initial scheduling information as a starting point for scheduling email deliveries. The system measures levels of content interaction by the recipients to gauge corresponding interest levels in the content. Using recipient interest levels as feedback, the content delivery system is able to modify and extend scheduling details to optimally schedule further deliveries of content.

Automatic scheduling of content delivery

Growing community of inventors

Menlo Park, CA, United States of America

Alexandre Lee