Automatically labeling clusters of media content consumers

Abstract

An analytics platform configured to create clusters of media content consumers and to automatically generate human-readable, text labels that describe each of the created clusters is disclosed. An analytics platform may use any of a number of clustering algorithms to group a population of media content consumers into a set of user clusters based on viewing history data, user profile data, and/or any other data associated with the consumers. Furthermore, the analytics platform may be configured to create, based on the viewing history data and/or other data associated with a selected sample of users from each cluster, a text label for each cluster. For example, if viewing history data for a population of users includes channel and genre identifiers associated with media content items accessed by users of the population, a generated text label may provide an indication of channels and/or genres popular with users of each particular cluster.

1 - 20 . (canceled) 
     
     
         21 . A method comprising:
 analyzing, by a server, media content viewing history of a plurality of users over a specified time range, wherein media content viewing history includes a plurality of genres;   creating a genre identifier for each genre from the plurality of genres;   creating a channel identifier for each of a plurality of channels accessed by the plurality of users;   identifying a cluster of users that accessed media content item of a particular genre of the plurality of genres and that accessed a particular channel of the plurality of channels; and   creating a composite text label for the particular genre identifier and the particular channel identifier, wherein the composite text label comprises a first portion based on the particular genre identifier and a second portion based on the particular channel identifier; and   storing the composite text label in association with the cluster of users.   
     
     
         22 . The method of  claim 21 , further comprising pattern mining, by the server, to identify a pattern of frequently accessed channels from the plurality of channels. 
     
     
         23 . The method of  claim 21 , further comprising pattern mining, by the server, to identify a pattern of frequently accessed genres from the plurality of genres. 
     
     
         24 . The method of  claim 21 , further comprising determining a number of times a media device associated with a user from the cluster of users accessed the media content item, wherein the media content item is identified by a media content identifier. 
     
     
         25 . The method of  claim 21 , further comprising displaying on a graphical user interface of a user, from the plurality of users, the composite text label with a visual representation of the cluster of users. 
     
     
         26 . The method of  claim 21 , further comprising displaying on a graphical user interface of a user, from the plurality of users, advertising related to the particular genre identifier. 
     
     
         27 . The method of  claim 21 , further comprising displaying on a graphical user interface of a user, from the plurality of users, advertising related to the composite text label. 
     
     
         28 . The method of  claim 21 , further comprising:
 determining an average viewing history based on a number of times users of the cluster of users accessed any media content item; and   selecting one or more sample users based on their viewing histories being similar to the average viewing history.   
     
     
         29 . The method of  claim 28  wherein the determining of the average viewing history if performed for each cluster of the cluster of users. 
     
     
         30 . The method of  claim 21 , wherein the composite text label is used to determine user engagement behavior. 
     
     
         31 . A system comprising:
 input circuitry of a device configured to receive media content viewing history of a plurality of users; and   control circuitry, connected to the input circuitry, configured to:
 analyze the media content viewing history of the plurality of users over a specified time range, wherein media content viewing history includes a plurality of genres; 
 create a genre identifier for each genre from the plurality of genres; 
 create a channel identifier for each of a plurality of channels accessed by the plurality of users; 
 identify a cluster of users that accessed media content item of a particular genre of the plurality of genres and that accessed a particular channel of the plurality of channels; and 
 create a composite text label for the particular genre identifier and the particular channel identifier, wherein the composite text label comprises a first portion based on the particular genre identifier and a second portion based on the particular channel identifier; and 
   store the composite text label in association with the cluster of users.   
     
     
         32 . The system of  claim 31 , further comprising displaying on a graphical user interface of a user, from the plurality of users, advertising related to the particular genre identifier. 
     
     
         33 . The system of  claim 31 , further comprising displaying on a graphical user interface of a user, from the plurality of users, advertising related to the composite text label. 
     
     
         34 . The system of  claim 31 , further comprising pattern mining to identify a pattern of frequently accessed genres from the plurality of genres. 
     
     
         35 . A non-transitory computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by one or more processors of an electronic device, cause the electronic device to:
 analyze media content viewing history of a plurality of users over a specified time range, wherein media content viewing history includes a plurality of genres;   create a genre identifier for each genre from the plurality of genres;   create a channel identifier for each of a plurality of channels accessed by the plurality of users;   identify a cluster of users that accessed media content item of a particular genre of the plurality of genres and that accessed a particular channel of the plurality of channels; and   create a composite text label for the particular genre identifier and the particular channel identifier, wherein the composite text label comprises a first portion based on the particular genre identifier and a second portion based on the particular channel identifier; and   store the composite text label in association with the cluster of users.   
     
     
         36 . The non-transitory computer-readable storage medium of  claim 35 , further comprising displaying on a graphical user interface of a user, from the plurality of users, advertising related to the particular genre identifier. 
     
     
         37 . The non-transitory computer-readable storage medium of  claim 35 , further comprising displaying on a graphical user interface of a user, from the plurality of users, advertising related to the composite text label. 
     
     
         38 . The non-transitory computer-readable storage medium of  claim 35 , further comprising:
 determining an average viewing history based on a number of times users of the cluster of users accessed any media content item; and   selecting one or more sample users based on their viewing histories being similar to the average viewing history.   
     
     
         39 . The non-transitory computer-readable storage medium of  claim 38 , wherein the determining of the average viewing history is performed for each cluster of the cluster of users. 
     
     
         40 . The non-transitory computer-readable storage medium of  claim 35 , wherein the composite text label is used to determine user engagement behavior.