Tunable chatbots

Patent metadata

Field	Value
Publication number	US-11381682-B2
Application number	US-202017107118-A
Country	US
Kind code	B2
Filing date	Nov 30, 2020
Priority date	May 18, 2020
Publication date	Jul 5, 2022
Grant date	Jul 5, 2022

Abstract

A contact center, communication system, and method of operating a contact center are provided. In one example, the contact center includes a plurality of chatbots stored in memory and a chatbot selector that determines a customer interaction in the contact center will have a chatbot assigned thereto, selects a chatbot from the plurality of chatbots for assigning to the customer interaction based on a match between a capability of the chatbot and a service requirement associated with the customer interaction, and assigns the selected chatbot to the customer interaction thereby enabling the selected chatbot to process inputs received during the customer interaction and provide responses to the inputs.

First claim

What is claimed is:

1. A method of processing messages received in a communication system, the method comprising:
receiving a contact from a customer communication device in a contact center;
determining a service requirement associated with the contact;
comparing the service requirement with capabilities of a plurality of different chatbots, wherein each of the plurality of different chatbots possesses a different set of capabilities;
selecting a chatbot from the plurality of different chatbots, wherein the chatbot is selected based on its set of capabilities best matching the service requirement associated with the contact and wherein the chatbot is tunable;
allowing the chatbot to engage in an interaction with the customer communication device for purposes of servicing the contact,
determining a personality trait that is more likely than not to be found desirable by a customer that initiated the contact, and
tuning, in real-time; a personality characteristic of the selected chatbot to provide the determined personality trait.

2. The method of claim 1 , wherein the selected chatbot is selected based on its ability to be tuned to provide the personality trait.

3. The method of claim 2 , wherein the personality characteristic comprises at least one of assertive, passive, quiet, permissive, conscientious, agreeable, extraverted, and introverted.

4. The method of claim 1 , wherein comparing the service requirement with the capabilities of the plurality of different chatbots comprises:
analyzing a range of a personality characteristic for each of the plurality of different chatbots as a probability curve;
specifying a parameter of the probability curve as a parameter of interest; and
determining the personality characteristic for each of the plurality of different chatbots by comparing the parameter of interest for each probability curve of each of the plurality of different chatbots.

5. The method of claim 4 , wherein the probability curve comprises a bell curve and wherein the parameter comprises a width of the bell curve.

6. The method of claim 1 , further comprising:
providing an output of the chatbot to a human agent prior to allowing the output to be transmitted to the customer communication device;
receiving an input from the human agent that verifies the output of the chatbot as acceptable to transmit to the customer communication device; and
in response to receiving the input from the human agent, transmitting the output of the chatbot to the customer communication device.

7. The method of claim 6 , wherein the output comprises a text-based output and wherein the output is transmitted via a digital communication channel.

8. The method of claim 6 , wherein the output comprises an audible output and wherein the output is transmitted via a voice or video communication channel.

9. The method of claim 6 , wherein the service requirement comprises a skill and wherein the capabilities comprise a skill set.

10. The method of claim 1 , wherein the service requirement comprises a personality trait and wherein the capabilities comprise a personality characteristic.

11. A communication system, comprising:
a processor; and
computer memory storing data thereon that enables the processor to:
receive a contact from a customer communication device in a contact center;
determine a service requirement associated with the contact;
compare the service requirement with capabilities of a plurality of different chatbots, wherein each of the plurality of different chatbots possesses a different set of capabilities;
select a chatbot from the plurality of different chatbots, wherein the chatbot is selected based on its set of capabilities best matching the service requirement associated with the contact and wherein the chatbot is tunable;
allow the chatbot to engage in an interaction with the customer communication device for purposes of servicing the contact;
determine a personality trait that is more likely than not to be found desirable by a customer that initiated the contact; and
tune, in real-time, a personality characteristic of the selected chatbot to provide the determined personality trait.

12. The communication system of claim 11 , wherein the data stored in memory further enables the processor to:
provide customer input to the plurality of different chatbots;
receive, from each of the plurality of different chatbots, candidate responses to the customer input; and
select the chatbot based on a candidate response provided by the chatbot.

13. The communication system of claim 12 , wherein the candidate response provided by the chatbot satisfies an optimization function better than candidate responses provided by other chatbots in the plurality of different chatbots.

14. The communication system of claim 13 , wherein the optimization function considers a benefit associated with the candidate response provided by the chatbot and benefits associated with the candidate responses provided by other chatbots.

15. The communication system of claim 13 , wherein the Optimization function considers a cost of using the chatbot and costs associated with using other chatbots.

16. The communication system of claim 11 , wherein the contact comprises a text-based message received via a digital communication channel.

17. The communication system of claim 11 , wherein the contact is received via a voice or video communication channel.

18. The communication system of claim 11 , wherein the processor and computer memory are provided as a quantum computer.

19. A contact center, comprising:
a plurality of chatbots stored in memory; and
a chatbot selector that determines a customer interaction in the contact center will have a chatbot assigned thereto, selects a chatbot from the plurality of chatbots for assigning to the customer interaction based on a match between a capability of the chatbot and a service requirement associated with the customer interaction, assigns the selected chatbot to the customer interaction thereby enabling the selected chatbot to process inputs received during the customer interaction and provide responses to the process inputs, and tunes a personality characteristic of the selected chatbot to provide a determined personality trait.

20. The contact center of claim 19 , wherein the chatbot selector is further configured to pre-test the plurality of chatbots prior to selecting the chatbot and based on a performance of each of the plurality of chatbots to the pre-test, select the chatbot from among the plurality of chatbots, wherein pre-test comprises providing an input received during the customer interaction to each of the plurality of chatbots and receiving candidate outputs from each of the plurality of chatbots.

Assignees

• Avaya Man Lp

Inventors

• Matula Valentine C
• Chavez David
• Grebovich Dragan

Classifications

• H04M3/527

  Centralised call answering arrangements not requiring operator intervention · CPC title

• H04M3/5166 Primary

  in combination with interactive voice response systems or voice portals, e.g. as front-ends · CPC title

• G06F40/56

  Natural language generation · CPC title

• H04L51/02

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

• G10L2015/225

  Feedback of the input speech · CPC title