Method and system for personalized recommendation modeling

摘要

A method and system for modeling the interests of an individual television viewer based on logging the user's television usage activities for the purpose of determining personalized recommendations is presented. According to one aspect of the claimed subject matter, user input in response to a questionnaire, the user's recorded television usage, the user's previous interactions with the personalized recommendations and contextual data such as external events and social group influences are used to model the probability of a user's interest in available media content. Data from the model is subsequently arranged to display units of available media content with the highest probabilities of user interest to the user. According to further embodiments, specific user behavior in previously consumed media content such as a user's selection, a user's continuous consumption, and a user's discontinuation of consumption is tracked and used as input.

主权项

1. A method for providing a personalized media content schedule for a user, the method comprising:
determining, in a processor of a computing device communicatively coupled to a display device, a plurality of units of available media content from a plurality of content sources; dynamically generating a schedule of recommended units of available media content from the plurality of units of available media content, the schedule being customized for a user of the display device; displaying to the user a graphical display of the schedule of recommended units of available media content, the display comprising an ordered listing of a plurality of recommended units from the schedule of recommended units of available media content arranged according to a relative predicted level of user interest in each of the plurality of units of available media content; and tracking user interaction with the schedule of recommended available units of media content, wherein the schedule of recommended available units of media content is customized for the user by generating a viewing profile for the user based at least on a plurality of past instances of user behavior corresponding to units of media content previously consumed by the user and mapped to the units of available media content, further wherein the viewing profile is used to predict the relative level of user interest in each of the plurality of units of the available media content by assigning weighted values to a plurality of extracted reasons contributing to the past instance of user behavior, and identifying a past instance of user behavior with the greatest weighted sum of values.