Contact center quality management control using generative artificial intelligence
A quality management output relative to agent performance during a contact center interaction is generated using a trained generative artificial intelligence model to automate the reporting and further action of such quality management output. Recording information associated with a contact center interaction between an agent and an end user is obtained. The recording information is processed using a generative artificial intelligence model to determine a quality management output for the contact center interaction. An agent report is then generated based on the quality management output and associated materials and provided to the agent, and, optionally, to a supervisor device associated with the agent. In some cases, a simulated contact center interaction may be generated to further train the agent based on the quality management output.
1 . A method, comprising:
generating, by a first large language model of a contact center system, a summary of a contact center interaction based on a transcription of the contact center interaction, wherein the contact center interaction is facilitated by the contact center system between an agent device and a user device and corresponds to a video communication modality or an asynchronous communication modality;
determining, by a second large language model of the contact center system retrieving recording information associated with the contact center interaction from a data store in which the recording information is stored and processing the recording information, a quality management output for the contact center interaction, wherein the recording information includes the summary of the contact center interaction and indicates an evaluation of agent performance during the contact center interaction;
generating, by the second large language model processing the quality management output, a simulated contact center interaction that includes simulated end user media to present to the agent device, wherein the simulated end user media includes video content configured for real-time response by an agent using the agent device and corresponds to the video communication modality; and
outputting, to the agent device, an agent report that includes a hyperlink usable for the agent device to access the simulated contact center interaction and respond to the video content.
2 . The method of claim 1 , comprising:
transmitting the agent report to a supervisor device associated with the agent.
3 . The method of claim 1 , wherein determining the quality management output for the contact center interaction comprises:
extracting, using the second large language model, insights from the recording information; and
determining the quality management output based on the insights.
4 . The method of claim 1 , wherein determining the quality management output for the contact center interaction comprises:
evaluating, using the second large language model, agent performance during the contact center interaction using the recording information to determine a score for the agent; and
determining the quality management output based on the score for the agent.
5 . The method of claim 1 , wherein outputting the agent report comprises:
including a timeline of insights with one or more comments generated using the second large language model within the agent report.
6 . The method of claim 1 , wherein the contact center interaction is facilitated via a video conference implemented by a contact center as a service platform.
7 . The method of claim 1 , wherein the contact center interaction includes a chat message conversation or text message conversation and the recording information corresponds to messages of the chat message conversation or of the text message conversation.
8 . The method of claim 1 , comprising:
filtering, by the second large language model, sensitive or private content of the recording information.
9 . A non-transitory computer readable medium storing instructions operable to cause one or more processors to perform operations comprising:
generating, by a first large language model of a contact center system, a summary of a contact center interaction based on a transcription of the contact center interaction, wherein the contact center interaction is facilitated by the contact center system between an agent device and a user device and corresponds to a video communication modality or an asynchronous communication modality;
determining, by a second large language model of the contact center system retrieving recording information associated with the contact center interaction from a data store in which the recording information is stored and processing the recording information, a quality management output for the contact center interaction, wherein the recording information includes the summary of the contact center interaction and indicates an evaluation of agent performance during the contact center interaction;
generating, by the second large language model processing the quality management output, simulated contact center interaction that includes simulated end user media to present to the agent device, wherein the simulated end user media includes video content configured for real-time response by an agent using the agent device and corresponds to the video communication modality; and
outputting, to the agent device, an agent report that includes a hyperlink usable for the agent device to access the simulated contact center interaction and respond to the video content.
10 . The non-transitory computer readable medium of claim 9 , wherein the quality management output is determined based on insights extracted from the recording information using the second large language model.
11 . The non-transitory computer readable medium of claim 9 , wherein the quality management output is determined based on a score determined by evaluating agent performance during the contact center interaction according to the recording information.
12 . The non-transitory computer readable medium of claim 9 , wherein the agent report is accessible to a supervisor device associated with the agent.
13 . The non-transitory computer readable medium of claim 9 , wherein the agent report visually represents comments generated using the second large language model in a timeline format.
14 . The non-transitory computer readable medium of claim 9 , wherein the second large language model filters sensitive or private content of the recording information.
15 . A system, comprising:
a memory subsystem; and
processing circuitry configured to execute instructions stored in the memory subsystem to:
generate, by a first large language model of a contact center system, a summary of a contact center interaction based on a transcription of the contact center interaction, wherein the contact center interaction is facilitated by the contact center system between an agent device and a user device and corresponds to a video communication modality or an asynchronous communication modality;
determine, by a second large language model of the contact center system retrieving recording information associated with the contact center interaction from a data store in which the recording information is stored and processing the recording information, a quality management output for the contact center interaction, wherein the recording information includes the summary of the contact center interaction and indicates an evaluation of agent performance during the contact center interaction;
generate, by the second large language model processing the quality management output, a simulated contact center interaction that includes simulated end user media to present to the agent device, wherein the simulated end user media includes video content configured for real-time response by an agent using the agent device and corresponds to the video communication modality; and
output, to the agent device, an agent report that includes a hyperlink usable for the agent device to access the simulated contact center interaction and respond to the video content.
16 . The system of claim 15 , wherein, to determine the quality management output for the contact center interaction, the processing circuitry is configured to execute the instructions to:
determine the quality management output based on insights extracted using the second large language model from the recording information.
17 . The system of claim 15 , wherein, to determine the quality management output for the contact center interaction, the processing circuitry is configured to execute the instructions to:
determine the quality management output based on a score determined for the agent by the second large language model evaluating agent performance during the contact center interaction using the recording information.
18 . The system of claim 15 , wherein the agent report includes a timeline of insights including one or more comments generated using the second large language model.
19 . The system of claim 15 , wherein the contact center interaction is facilitated using a synchronous communication service of a unified communications as a service software platform or of a contact center as a service platform.
20 . The system of claim 15 , wherein sensitive or private content of the recording information is filtered to determine the quality management output.