Systems and methods for adaptive emotion based automated emails and/or chat replies
Efficient and effective communications with customers is a cornerstone of many businesses. Automation, such as in the form of automated agents that can engage in a communication with a customer, furthers those efficient and effective communications. However, textual messages are a series of messages that are often limited to factual statements and direct questions, leaving many customers, such as those that prefer or require high-context communications, may have the impression that the organization with which they are communicating is cold and uncaring or unconcerned about them. By selectively altering the series of messages, an appropriate degree of concern or empathy may be conveyed to facilitate a better relationship and more effective and efficient communications.
1. A system, comprising:
a network interface to a network;
a microprocessor; and
wherein the microprocessor performs:
accessing a communication between a customer communication device, utilized by a customer, and an automated agent, wherein the communication comprises text;
determining a purpose of the communication;
selecting, for presentation within the communication, a number of reply messages previously determined to resolve the purpose of the communication and having a presentation emotion, wherein the presentation emotion is initially a default emotion;
determining a target emotion for the communication to present to the customer;
upon determining the default emotion has a difference from the target emotion, selecting at least one alternate message, from a pool of alternate messages, to insert into the communication to modify the presentation emotion and attenuate the difference from the target emotion; and
present the communication, comprising the modification to the presentation emotion, to the customer communication device for presentation to the customer.
2. The system of claim 1 wherein the microprocessor performs selecting the at least one alternate message from a machine learned model of a pool of prior communications wherein the presentation emotion was modified from the default emotion with at least one alternate message selected from the pool of alternate messages.
3. The system of claim 1 wherein the microprocessor performs inserting the alternate message and further removes at least one of the number of reply messages.
4. The system of claim 1 wherein the microprocessor performs inserting the alternate message comprising altering the text of at least one of the number of reply messages.
5. The system of claim 1 , wherein the target emotion is determined from a subject matter of the purpose.
6. The system of claim 1 , wherein the target emotion is determined from a cultural background of the customer.
7. The system of claim 6 , wherein the cultural background of the customer is determined from a location of the customer.
8. The system of claim 1 , wherein the target emotion is determined from an analysis of the text portion provided by the customer.
9. The system of claim 1 , wherein the target emotion is determined from one or more of a known personality trait of the customer.
10. The system of claim 1 , wherein the microprocessor further performs, determining that the difference between the default emotion and the target emotion is a difference greater than the attenuation, connecting the communication to a communication device associated with an agent and prompting the agent to provide a portion of the communication.
11. A method, comprising:
accessing a communication between a customer communication device, utilized by a customer, and an automated agent, wherein the communication comprises text;
determining a purpose of the communication;
selecting, for presentation within the communication, a number of reply messages previously determined to resolve the purpose of the communication and having a presentation emotion, wherein the presentation emotion is initially a default emotion;
determining a target emotion for the communication to present to the customer;
upon determining the default emotion has a difference from the target emotion, selecting at least one alternate message, from a pool of alternate messages, to insert into the communication to modify the presentation emotion and attenuate the difference from the target emotion; and
present the communication, comprising the modification to the presentation emotion, to the customer communication device for presentation to the customer.
12. The method of claim 11 , wherein selecting the at least one alternate message from a machine learned model of a pool of prior communications wherein the presentation emotion was modified from the default emotion with at least one alternate message selected from the pool of alternate messages.
13. The method of claim 11 wherein inserting the alternate message and further comprises removing at least one of the number of reply messages.
14. The method of claim 11 wherein the inserting the alternate message comprising altering the text of at least one of the number of reply messages.
15. The method of claim 11 , wherein the target emotion is determined from a subject matter of the purpose.
16. The method of claim 11 , wherein the target emotion is determined from a cultural background of the customer.
17. The method of claim 16 , wherein the cultural background of the customer is determined from a location of the customer.
18. The method of claim 11 , wherein the target emotion is determined from an analysis of the text portion provided by the customer.
19. A system, comprising:
means to accesses a communication between a customer communication device, utilized by a customer, and an automated agent, wherein the communication comprises text;
means to determine a purpose of the communication;
means to select, for presentation within the communication, a number of reply messages previously determined to resolve the purpose of the communication and having a presentation emotion, wherein the presentation emotion is initially a default emotion;
means to determine a target emotion for the communication to present to the customer;
means to, upon determining the default emotion has a difference from the target emotion, selecting at least one alternate message, from a pool of alternate messages, to insert into the communication to modify the presentation emotion and attenuate the difference from the target emotion; and
means to present the communication, comprising the modification to the presentation emotion, to the customer communication device for presentation to the customer.
20. The system of claim 19 wherein the means to select the at least one alternate message comprises means to select the at least one alternate message from a machine learned model of a pool of prior communications wherein the presentation emotion was modified from the default emotion with at least one alternate message selected from the pool of alternate messages.