System and method for providing unsupervised learning to associate profiles in video audiences

Abstract

A system and method for providing unsupervised learning to associate profiles in video audiences is provided. The method includes: receiving a zapping log and a broadcast schedule, wherein the zapping log includes records of set top box zapping signatures for at least a portion of the set top boxes of the network; deriving set top box signatures from the zapping log and broadcast schedule; clustering viewer profiles into groups of viewer profiles using the set top box signatures; and associating at least one set top box within the network with at least one viewer profile, wherein the method of performing unsupervised learning does not use data associating demographic or psychographic profiles to the at least a portion of the set top boxes of the network for which the zapping log contains records of set top box zapping signatures.

1 . A method of performing unsupervised learning to associate viewer profiles in video audiences of a network, comprising the steps of:
 receiving a zapping log and a broadcast schedule, wherein the zapping log includes records of set top box zapping signatures for at least a portion of the set top boxes of the network;   deriving set top box signatures from the zapping log and broadcast schedule;   clustering viewer profiles into groups of viewer profiles using the set top box signatures; and   associating at least one set top box within the network with at least one viewer profile,
 wherein the method of performing unsupervised learning does not use data associating demographic or psychographic profiles to the at least a portion of the set top boxes of the network for which the zapping log contains records of set top box zapping signatures. 
   
     
     
         2 . The method of  claim 1 , wherein said zapping signatures include events where there is a switching from a current service to another service and/or other means for communicating with the set top box. 
     
     
         3 . The method of  claim 1 , further comprising the step of determining a targeted rating of a content per profile and a regional targeted rating. 
     
     
         4 . The method of  claim 1 , further comprising the step of determining a total viewership. 
     
     
         5 . The method of  claim 1 , further comprising the step of determining a viewership flow per a pre-defined time step. 
     
     
         6 . The method of  claim 1 , further comprising the step of determining a content to profile assignment. 
     
     
         7 . The method of  claim 1 , wherein the set top box signatures comprise at least one signature for each set top box in the network. 
     
     
         8 . The method of  claim 7 , wherein the set top box signatures may include at least one class of signature selected from the group consisting of viewing signatures, time signatures, high-resolution time signatures, and zapping frequency signatures. 
     
     
         9 . The method of  claim 1 , wherein the groups of viewer profiles resulting from the step of clustering are unresolved viewer profiles, where a type of the viewer profile is not known. 
     
     
         10 . The method of  claim 9 , wherein an optimization algorithm is used to perform the step of clustering. 
     
     
         11 . The method of  claim 9 , further comprising the step of matching the unresolved viewer profiles and predefined profiles, to provide resolved viewer profiles. 
     
     
         12 . The method of  claim 11 , wherein the step of matching further comprises performing a best match procedure on both the unresolved viewer profiles and the predefined profiles. 
     
     
         13 . The method of  claim 11 , wherein the step of associating at least one set top box within the network with at least one viewer profile uses the resolved viewer profiles with the set top box signatures as input. 
     
     
         14 . The method of  claim 1 , wherein the step of associating at least one set top box within the network with at least one viewer profile uses a quantization process. 
     
     
         15 . The method of  claim 1 , wherein the step of associating at least one set top box within the network with at least one viewer profile further comprises providing a relationship between a matrix A, a matrix B, and a matrix C, where matrix A multiplied by matrix B approximates matrix C, where A represents a set of parameters representing the association of at least one profile to set top boxes, B represents an aggregation of targeted rating probabilities of each of the viewer profiles per each content watched by at least a portion of the set top boxes of the network for which the zapping log contains records of set top box zapping signatures, and C is an aggregation of the set top box signatures. 
     
     
         16 . The method of  claim 14 , wherein the quantization process further comprises calculating a mean and variance. 
     
     
         17 . A system for providing unsupervised learning to associate consumer profiles in video audiences, wherein the system comprises a head end having a computer and means for communicating therein, wherein the computer has a management application stored therein, and wherein the management application further comprises:
 logic configured to receive a zapping log and a broadcast schedule, wherein the zapping log includes records of set top box zapping signatures for at least a portion of the set top boxes of the network;   logic configured to derive set top box signatures from the zapping log and broadcast schedule;   logic configured to cluster viewer profiles into groups of viewer profiles using the set top box signatures; and   logic configured to associate at least one set top box within the network with at least one viewer profile,
 wherein performing unsupervised learning does not use data associating demographic or psychographic profiles to the at least a portion of the set top boxes of the network for which the zapping log contains records of set top box zapping signatures. 
   
     
     
         18 . The system of  claim 17 , wherein said zapping signatures include events where there is a switching from a current service to another service and/or other means for communicating with the set top box. 
     
     
         19 . The system of  claim 17 , wherein the management application further comprises logic configured to determine a targeted rating of a content per profile and a regional targeted rating. 
     
     
         20 . The system of  claim 17 , wherein the management application further comprises logic configured to determine a total viewership. 
     
     
         21 . The system of  claim 17 , wherein the management application further comprises logic configured to determine a viewership flow per a pre-defined time step. 
     
     
         22 . The system of  claim 17 , wherein the management application further comprises logic configured to determine a content to profile assignment. 
     
     
         23 . The system of  claim 17 , wherein the set top box signatures comprise at least one signature for each set top box in the network. 
     
     
         24 . The system of  claim 23 , wherein the set top box signatures include at least one class of signature selected from the group consisting of viewing signatures, time signatures, high-resolution time signatures, and zapping frequency signatures. 
     
     
         25 . The system of  claim 17 , wherein the groups of viewer profiles resulting from clustering are unresolved viewer profiles, where a type of the viewer profile is not known. 
     
     
         26 . The system of  claim 25 , wherein an optimization algorithm is used to perform clustering. 
     
     
         27 . The system of  claim 25 , wherein the management application further comprises logic configured to match the unresolved viewer profiles and predefined profiles, to provide resolved viewer profiles. 
     
     
         28 . The system of  claim 27 , wherein matching further comprises performing a best match procedure on both the unresolved viewer profiles and the predefined profiles. 
     
     
         29 . The system of  claim 27 , wherein associating at least one set top box within the network with at least one viewer profile uses the resolved viewer profiles with the set top box signatures as input. 
     
     
         30 . The system of  claim 29 , wherein associating at least one set top box within the network with at least one viewer profile uses a quantization process. 
     
     
         31 . The system of  claim 17 , wherein associating at least one set top box within the network with at least one viewer profile further comprises providing a relationship between a matrix A, a matrix B, and a matrix C, where matrix A multiplied by matrix B approximates matrix C, where A represents a set of parameters representing the association of at least one profile to set top boxes, B represents an aggregation of targeted rating probabilities of each of the viewer profiles per each content watched by at least a portion of the set top boxes of the network for which the zapping log contains records of set top box zapping signatures, and C is an aggregation of the set top box signatures.