US-12620393-B2 - Technologies for leveraging machine learning to predict empathy for improved contact center interactions

US12620393B2US 12620393 B2US12620393 B2US 12620393B2US-12620393-B2

Abstract

A method of leveraging machine learning to predict empathy for improved contact center interactions according to an embodiment includes receiving, by a computing system, at least one user message from a real-time contact center interaction with a user, generating, by an artificial intelligence system of the computing system, at least one empathy score based on the at least one message using the machine learning, wherein each of the at least one empathy score is indicative of a real-time empathy of the user, generating, by the artificial intelligence system of the computing system, an empathetic text response to the at least one user message based on the at least one empathy score, and responding to the at least one user message in the real-time contact center interaction based on the empathetic text response generated by the artificial intelligence system of the computing system.

Inventors

Mohamed Uvaiz Anwar Batcha
Monisha Padmavathi Ragavan
Praveen Kumar Anandadoss
Asmitha Durairaj
Vinoth Subramaniam

Assignees

GENESYS CLOUD SERVICES, INC.

Dates

Publication Date: 20260505
Application Date: 20231003

Claims (13)

1 . A method of leveraging machine learning to predict empathy for improved contact center interactions, the method comprising: receiving, by a computing system, at least one user message from a real-time contact center interaction with a user between the user and a human contact center agent; generating, by an artificial intelligence system of the computing system, at least one empathy score based on the at least one message using the machine learning, wherein each of the at least one empathy score is indicative of a real-time empathy of the user, and wherein generating the at least one empathy score based on the at least one message using the machine learning comprises: determining a high level empathy category of the user selected from a first group of categories; determining a deep level empathy category of the user selected from a second group of categories different from the first group of categories; and determining a language style category of the user selected from a third group of categories different from the first group of categories and the second group of categories; receiving, by the computing system, a draft agent response to the at least one user message by the human contact center agent; auto-suggesting, by the artificial intelligence system of the computing system, an empathetic agent response to the at least one user message based on the draft agent response and the at least one empathy score; and responding, via an agent device of the human contact center agent, to the at least one user message in the real-time contact center interaction based on the empathetic agent response auto-suggested by the artificial intelligence system of the computing system.
2 . The method of claim 1 , wherein determining the high level empathy category of the user comprises selecting a high level empathy category of the user from a group of high level empathy categories consisting of anger, joyfulness, optimism, and sadness.
3 . The method of claim 1 , wherein determining the deep level empathy category of the user comprises selecting a deep level empathy category of the user from a group of at least ten different categories of deep level empathies.
4 . The method of claim 1 , wherein determining the deep level empathy category of the user comprises selecting a deep level empathy category of the user from a group of deep level empathy categories consisting of sentimental, afraid, proud, faithful, terrified, jealous, grateful, prepared, embarrassed, excited, annoyed, lonely, ashamed, guilty, surprised, nostalgic, confident, furious, disappointed, caring, trusting, disgusted, anticipating, anxious, hopeful, impressed, apprehensive, and devastated.
5 . The method of claim 1 , wherein determining the language style category of the user comprises selecting a language style category of the user from a group of language style categories consisting of confident, analytical, and determinant.
6 . A system for leveraging machine learning to predict empathy for improved contact center interactions, the system comprising: at least one processor; and at least one memory comprising a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the system to: receive at least one user message from a real-time contact center interaction with a user between the user and a human contact center agent; generate, by an artificial intelligence system, at least one empathy score based on the at least one message using the machine learning, wherein each of the at least one empathy score is indicative of a real-time empathy of the user, and wherein to generate the at least one empathy score based on the at least one message using the machine learning comprises to: determine a high level empathy category of the user selected from a first group of categories; determine a deep level empathy category of the user selected from a second group of categories different from the first group of categories; and determine a language style category of the user selected from a third group of categories different from the first group of categories and the second group of categories; receive a draft agent response to the at least one user message by the human contact center agent; generate, by the artificial intelligence system, an empathetic agent response to the at least one user message based on the draft agent response and the at least one empathy score; and transmit the empathetic agent response to an agent device of the human contact center agent for empathetic reply to the at least one user message by the human contact center agent.
7 . The system of claim 6 , wherein to determine the high level empathy category of the user comprises to select a high level empathy category of the user from a group of high level empathy categories consisting of anger, joyfulness, optimism, and sadness.
8 . The system of claim 6 , wherein to determine the deep level empathy category of the user comprises to select a deep level empathy category of the user from a group of at least ten different categories of deep level empathies.
9 . The system of claim 6 , wherein to determine the language style category of the user comprises to select a language style category of the user from a group of language style categories consisting of confident, analytical, and determinant.
10 . A method of leveraging machine learning to predict empathy for improved contact center interactions, the method comprising: receiving, by a computing system, at least one user message from a real-time contact center interaction with a user between the user and a chatbot; generating, by an artificial intelligence system of the computing system, at least one empathy score based on the at least one message using the machine learning, wherein each of the at least one empathy score is indicative of a real-time empathy of the user; generating, by the artificial intelligence system of the computing system, an empathetic text response to the at least one user message based on the at least one empathy score; transferring the real-time contact center interaction with the user to a human contact center agent; notifying the artificial intelligence system of the computing system that the real-time contact center interaction is transferred to the human contact center agent; and transmitting the at least one empathy score to an agent device of the human contact center agent.
11 . The method of claim 10 , further comprising: receiving, by the computing system, a draft agent response to the at least one user message by the human contact center agent; auto-suggesting, by the artificial intelligence system of the computing system, an empathetic agent response to the at least one user message based on the draft agent response and the at least one empathy score; and responding, via the agent device of the human contact center agent, to the at least one user message in the real-time contact center interaction based on the empathetic agent response auto-suggested by the artificial intelligence system of the computing system.
12 . The method of claim 11 , further comprising displaying a set of reply options to the human contact center agent on a graphical user interface of the agent device, wherein the set of reply options includes a first option to respond to the at least one user message using the auto-suggested empathetic agent response and a second option to respond to the at least one user message using an alternative to the auto-suggested empathetic agent response.
13 . The method of claim 12 , wherein the alternative to the auto-suggested empathetic agent response comprises the draft agent response.

Description

BACKGROUND Call centers and other contact centers are used by many organizations to provide technical and other support to their end users. The end user may interact with human and/or virtual agents of the contact center by establishing electronic communications via one or more communication technologies including, for example, telephone, email, web chat, Short Message Service (SMS), dedicated software application(s), and/or other technologies. Contact center agents may rely on knowledge bases and/or other resources in order to answer questions posed by end users, and expectations are now higher than ever for improved user experiences with contact centers. Although contact centers have traditionally measured user experience based on efficiency (i.e., doing things quickly) and effectiveness (i.e., doing things well), in today's world, efficiency and effectiveness are no longer enough to satisfy the ever-increasing expectations of contact center users. SUMMARY One embodiment is directed to a unique system, components, and methods for leveraging machine learning to predict empathy for improved contact center interactions. Other embodiments are directed to apparatuses, systems, devices, hardware, methods, and combinations thereof for leveraging machine learning to predict empathy for improved contact center interactions. According to an embodiment, a method of leveraging machine learning to predict empathy for improved contact center interactions may include receiving, by a computing system, at least one user message from a real-time contact center interaction with a user, generating, by an artificial intelligence system of the computing system, at least one empathy score based on the at least one message using the machine learning, wherein each of the at least one empathy score is indicative of a real-time empathy of the user, generating, by the artificial intelligence system of the computing system, an empathetic text response to the at least one user message based on the at least one empathy score, and responding to the at least one user message in the real-time contact center interaction based on the empathetic text response generated by the artificial intelligence system of the computing system. In some embodiments, the real-time contact center interaction with the user may be a real-time contact center interaction between the user and a chatbot of the contact center. In some embodiments, responding to the at least one user message in the real-time contact center interaction may include responding with the empathetic text response via the chatbot. In some embodiments, the method may further include transferring the real-time contact center interaction with the user to a contact center agent, notifying the artificial intelligence system of the computing system that the real-time contact center interaction is transferred to the contact center agent, and transmitting the at least one empathy score to an agent device of the contact center agent. In some embodiments, generating the at least one empathy score based on the at least one message using the machine learning may include determining a high level empathy of the user. In some embodiments, generating the at least one empathy score based on the at least one message using the machine learning may include determining a deep level empathy of the user. In some embodiments, determining the deep level empathy of the user may include selecting a deep level empathy of the user from a group of at least ten different categories of deep level empathies. In some embodiments, determining the deep level empathy of the user may include selecting a deep level empathy of the user from a group of deep level empathies consisting of sentimental, afraid, proud, faithful, terrified, jealous, grateful, prepared, embarrassed, excited, annoyed, lonely, ashamed, guilty, surprised, nostalgic, confident, furious, disappointed, caring, trusting, disgusted, anticipating, anxious, hopeful, impressed, apprehensive, and devastated. In some embodiments, generating the at least one empathy score based on the at least one message using the machine learning may include determining a language style of the user. In some embodiments, the real-time contact center interaction with the user may be a real-time contact center interaction between the user and a contact center agent, and the method may further include receiving, by the computing system, a draft agent response to the at least one user message by the contact center agent, and auto-suggesting, by the artificial intelligence system of the computing system, an empathetic agent response to the at least one user message based on the draft agent response and the at least one empathy score. In some embodiments, the method may further include replying, via an agent device of the contact center agent, to the at least one user message based on the empathetic agent response auto-suggested by the artificial intelligence system of the computing syste