Optimizing interaction results using AI-guided manipulated video
Real-time modification of video images of humans allows for the video to be modified so that an expression of a subject human may be changed. Customer service agents may have more successful interactions with customers if they display an appropriate facial expression, such as to provide a particular emotional state. By determining an appropriate facial expression, and any deviation from a customer service agent's current expression, a modification to the video image of the customer service agent may be determined and applied. As a result, agents may not have a facial expression that is best suited to successfully resolve a purpose of the interaction, to have the customer be presented with the best-suited facial expression.
1. A system for providing a situationally-matched expression in a video image, comprising:
a communication interface configured to receive a video image of a human agent engaged in an interaction via a network with a customer utilizing a customer communication device;
a processor having an accessible memory;
a data storage configured to maintain data records accessible to the processor; and
the processor configured to:
receive the video image of the human agent;
determine a desired facial expression of the human agent;
modify the video image of the human agent to comprise the desired facial expression; and
present the customer communication device with a modified video image of the human agent.
2. The system of claim 1 , wherein determining the desired facial expression of the human agent comprises, accessing a record in the data records having a topic matching a topic of the interaction and wherein the record identifies the desired facial expression.
3. The system of claim 1 , wherein determining the desired facial expression of the human agent comprises, accessing a current customer attribute of the customer and a record in the data records having a stored customer attribute matching the current customer attribute and wherein the record identifies the desired facial expression.
4. The system of claim 1 , wherein determining the desired facial expression of the human agent comprises, accessing a record in the data records having a desired customer impression of a human agent attribute matching a topic of the interaction and wherein the record identifies the desired facial expression.
5. The system of claim 1 , further comprising the processor storing, in the data storage, at least one of the video image or the modified video image.
6. The system of claim 1 , wherein the processor modifies the video image of the human agent to comprise the desired facial expression, comprising applying alterations to polygons mapping portions of the video image of the human agent in accordance with alteration data maintained in the data storage.
7. The system of claim 1 , wherein:
the processor modifies the video image of the human agent to comprise the desired facial expression, upon first determining a current facial expression; and
the processor determines the current facial expression is a mismatch to the desired facial expression.
8. The system of claim 7 , wherein the processor determines the current facial expression is a mismatch to the desired facial expression, upon determining the current facial expression and the desired facial expression provide a same expression with a mismatched degree of the same expression.
9. The system of claim 1 , further comprising the processor storing, in the data storage, indicia of success of the interaction and associated at least one of the desired facial expression or a current facial expression of the human agent.
10. The system of claim 9 , wherein the processor determines the desired facial expression of the human agent comprising determining the at least one of the desired facial expression or the current facial expression of the human agent having the indicia of success stored in the data storage.
11. A method, comprising:
receiving a video image of a human agent engaged in an interaction over a network with a customer via an associated customer communication device;
determining a desired facial expression of the human agent;
modifying the video image of the human agent to comprise the desired facial expression; and
presenting the associated customer communication device with a modified video image of the human agent.
12. The method of claim 11 , wherein the determining the desired facial expression of the human agent further comprises, accessing a record in a data storage having a topic matching a topic of the interaction and wherein the record identifies the desired facial expression.
13. The method of claim 11 , wherein the determining the desired facial expression of the human agent further comprises, accessing a current customer attribute of the customer in a record in a data storage having a stored customer attribute matching the current customer attribute and wherein the record identifies the desired facial expression.
14. The method of claim 11 , wherein the determining the desired facial expression of the human agent further comprises, accessing a record in a data record having a desired customer impression of a human agent attribute matching a topic of the interaction and wherein the record identifies the desired facial expression.
15. The method of claim 11 , further comprising storing, in a data storage, at least one of the video image or the modified video image.
16. The method of claim 11 , wherein the modifying of the video image of the human agent to comprise the desired facial expression, further comprises applying alterations to polygons mapping portions of the video image of the human agent in accordance with alteration data maintained in a data storage.
17. The method of claim 11 , wherein the modifying of the video image of the human agent to comprise the desired facial expression, further occurs upon first determining a current facial expression and determining the current facial expression is a mismatch to the desired facial expression.
18. The method of claim 17 , determining the current facial expression is a mismatch to the desired facial expression, further comprises determining the current facial expression and the desired facial expression provide a same expression with a mismatched degree of the same expression.
19. The method of claim 11 , further comprising storing, in data storage, indicia of success of the interaction and associated at least one of the desired facial expression or a current facial expression of the human agent.
20. A system: comprising:
means to receive a video image of a human agent engaged in an interaction over a network with a customer via an associated customer communication device;
means to determine a desired facial expression of the human agent, wherein the desired facial expression is selected in accordance with a facial expression associated with an attribute of the interaction and a successful outcome for past interaction having the attribute;
means to modify the video image of the human agent to comprise the desired facial expression; and
means to present the customer communication device with a modified video image of the human agent.