CPC G06Q 30/0276 (2013.01) [G06Q 30/0267 (2013.01); G06Q 30/0277 (2013.01)] | 16 Claims |
1. A computer-implemented method, the method comprising:
receiving, at a campaign management server, exemplary campaign messages, wherein the exemplary campaign messages comprise email messages and text messages in a first order;
generating an ensemble classification model comprising a logic-rule model, a first language model, and a second language model configured to independently generate a predicted characteristic tag;
generating layout data by extracting size, location, and visibility data of image or text components of the exemplary campaign messages;
predicting, via the ensemble classification model, a characteristic tag associated with each of the exemplary campaign messages at least partially based on the generated layout data;
receiving the characteristic tag associated with each of the exemplary campaign messages;
sorting the exemplary campaign messages based on the characteristic tag and one or more predetermined diversity preference rules to generate a respective list of sorted exemplary email messages and sorted exemplary text messages in a second order; and
displaying the respective list of exemplary email messages and exemplary text messages to a prospective campaign generator based on the respective list of sorted exemplary email messages and sorted exemplary text messages.
|