System and method for delivering personalized content based on deep learning of user emotions

Abstract

Disclosed are a system, method and software to associate attributes with digital media assets using deep learning. Digital media contains specific assets, such as audio, that can be replaced with other assets. The system, method and software allow for personalizing digital media content based in part on neural network analysis to learn a user's emotional state.

What is claimed is: 
     
         1 . A method for delivering personalized content based on learned emotions of a user, comprising:
 capturing, by a server, a plurality of user interactions performed over time with a digital media stream, wherein each user interaction is associated with a respective time point;   correlating, by the server, each user interaction to an emotional state;   learning, by a learning algorithm communicatively coupled to the server, based on the correlations, the emotional state of the user at each respective time point; and   serving, by the server, a new digital media stream based on the learned emotional states.   
     
     
         2 . The method of  claim 1 , wherein the learning utilizes an artificial intelligence method. 
     
     
         3 . The method of  claim 1 , further comprising updating a user profile with the learned emotional states. 
     
     
         4 . The method of  claim 1 , wherein the user interactions are selected from a group comprising at least one of a viewing habit, a purchase, a selection, and an answer to a question. 
     
     
         5 . The method of  claim 1 , wherein the emotional state is selected from a group comprising at least one of a happiness and sadness. 
     
     
         6 . The method of  claim 1 , wherein the emotional state is an indication of the user's affinity toward the digital media stream. 
     
     
         7 . The method of  claim 1 , wherein the emotional state is captured by an input indicating a like or dislike by a user. 
     
     
         8 . The method of  claim 1 , wherein the serving utilizes a neural network to select the new digital media stream based on the learned emotional states. 
     
     
         9 . A system for delivering personalized content based on learned emotions of a user, comprising:
 a server configured to receive a plurality of user interactions performed over time with a digital media stream;   a content server configured to store the digital media stream and transmit the digital media stream to the server;   a correlation algorithm communicatively coupled to the server, the correlation algorithm configured to correlate each user interaction to an emotional state; and   a learning module communicatively coupled to the server, the learning module configured to learn the emotional state of the user at each respective time point based on the correlations,   wherein the server is configured to serve a new digital media stream based on the learned emotional states.   
     
     
         10 . The system of  claim 9 , wherein the learning module utilizes an artificial intelligence method. 
     
     
         11 . The system of  claim 9 , wherein the server is further configured to update a user profile with the learned emotional states. 
     
     
         12 . The system of  claim 9 , wherein the user interactions are selected from a group comprising at least one of a viewing habit, a purchase, a selection, and an answer to a question. 
     
     
         13 . The system of  claim 9 , wherein the emotional state is selected from a group comprising at least one of happiness and sadness. 
     
     
         14 . The system of  claim 9 , wherein the emotional state is an indication of the user's affinity toward the digital media stream. 
     
     
         15 . The system of  claim 9 , wherein the emotional state is captured by an input by the user indicating a like or dislike. 
     
     
         16 . The system of  claim 9 , wherein the server utilizes a neural network to select the new digital media stream based on the learned emotional states. 
     
     
         17 . A method of delivering personalized content based on learned emotions of a user, comprising:
 capturing, by a server, a plurality of user interactions performed over time with a video stream, wherein each user interaction is associated with a respective time point;   correlating, by the server each user interaction to a like or a dislike;   learning, by a learning algorithm communicatively coupled to the server, based on the correlations, an emotional state of the user at each respective time point; and   serving, by the server, a new digital media stream based on the learned emotional states.   
     
     
         18 . The method of  claim 17 , wherein the learning utilizes an artificial intelligence method. 
     
     
         19 . The method of  claim 17 , wherein the video stream is selected from a group comprising at least one of a movie, a television show, and an advertisement. 
     
     
         20 . The method of  claim 17 , wherein the serving utilizes a neural network to select the new digital media stream based on the learned emotional states.