System architecture for universal emotive autography

An emotive autography apparatus, comprising:

• a selective supervised learning module configured to calculate a plurality of classifiers associated with an individual user, each of the classifiers indicating a preference of the user for an associated type of content;
• a segmentation module configured to divide received data into semantically similar segments;
• a segments classification and scoring module communicatively coupled to the segmentation module and to the selective supervised learning module, the segments classification and scoring module being configured to assign a respective preference score to each of the semantically similar segments by use of the classifiers;
• a segment sequencer communicatively coupled to the segments classification and scoring module and configured to arrange the semantically similar segments in a sequential order, the arranging being performed dependent upon the preference scores;
• and
• a blender module communicatively coupled to the segment sequencer and configured to present an emotive autograph based on the semantically similar segments arranged in the sequential order.

An emotive autography system, comprising:

• a concept discovery module configured to:
• receive a plurality of sets of data, each set of data being associated with a respective user;
• segment and cluster the data into clusters of semantically similar segments;
• a concept selection module communicatively coupled to the concept discovery module and configured to tag each of the clusters with a semantically meaningful tag;
• a selective supervised learning module communicatively coupled to the concept selection module and configured to train a respective set of classifiers for each of the clusters for each of the users, the training being performed by use of the semantically meaningful tags;
• a segments classification and scoring module communicatively coupled to the selective supervised learning module, the segments classification and scoring module being configured to assign a respective preference score to each of the semantically similar segments by use of the classifiers;
• a segment sequencer communicatively coupled to the segments classification and scoring module and configured to arrange the semantically similar segments in a sequential order, the arranging being performed dependent upon the preference scores;
• and
• a blender module communicatively coupled to the segment sequencer and configured to present an emotive autograph based on the semantically similar segments arranged in the sequential order.

A tangible, non-transitory, computer-readable medium comprising instructions that, when executed by a processor, direct the processor to:

• calculate a plurality of classifiers associated with an individual user, each of the classifiers indicating a preference of the user for an associated type of content;
• divide received data into semantically similar segments;
• assign a respective preference score to each of the semantically similar segments by use of the classifiers;
• arrange the semantically similar segments in a sequential order, the arranging being performed dependent upon the preference scores;
• and
• present an emotive autograph based on the semantically similar segments arranged in the sequential order.