System and method for cohort based content filtering and display
OwnerAlbert Rosato, Paul Corninginventors
Life of this patent
Estimating the term…
Abstract
A Cohort based content filtering and display system and method that enable users to obtain near-real-time information about how specific groups of users react to news, products, people, or other items. The system will aggregate and display commercially valuable, near-real-time information about user preferences and attitudes, sorted according to standard demographic and other user categories employed by marketers, research organizations and others, without compromising individual privacy. In some embodiments, a user can select a Cohort of interest to him or her, and then see what is most relevant to that Cohort, even if this user is not a member of the selected Cohort.
Claims20
A method for recommending content items to users, the method comprising:
- providing a database;
- providing an address accessible to at least one user, via a computer system, for interactive communications between said at least one user and said database;
- providing an interface to enable a plurality of individuals to supply demographic, psychographic, and other information about themselves;
- collecting records of demographic, psychographic, and other information about a plurality of individuals into said database;
- collecting behavioral information about users, including their preferences for or against arbitrarily defined sets of items;
- creating, in the database, a profile for each user;
- calculating aggregate similarity between individuals according to aggregated similarity of weighted measures of arbitrarily selected demographic, psychographic, or other individual attributes;
- identifying a plurality of items to be evaluated for recommendation to users;
- generating item preference scores to measure individuals' attitudes toward, or preferences for, the items or item metadata based on a dataset of user selections;
- defining user Cohorts according to calculated aggregate similarities between individuals;
- calculating content relevance to individual users or user Cohorts;
- generating Cohort-specific item recommendation scores by aggregating item preference scores of the individuals in a Cohort;
- selecting items for display to users according to cohort-specific recommendation scores;
- and
- displaying a list of items selected according to cohort-specific recommendation scores.
Dependencies are inferred from the claim text.