Platform for call transcription and summarization using generative artificial intelligence
View Patent ↗A system and method for call transcription and summarization using generative artificial intelligence. The system combines Automatic Speech Recognition (ASR) technology to transcribe customer-call center agent conversations and a Generative AI (GAI) model for summarization. It starts by processing the audio conversation, converting spoken words into text using ASR. Then, the GAI model is employed to generate a coherent, concise summary of the transcribed conversation. The GAI model understands context, key points, and intent, allowing it to create summaries that capture essential information. It can handle diverse conversations, adapt to different languages, and handle various accents and speech patterns. The resulting summaries help call center agents review and respond to customer inquiries more efficiently, enhancing customer service quality and decision-making.
1. A system for transcription and summarization using generative artificial intelligence, comprising:
a computing device comprising a processor, a memory, and a non-volatile data storage device;
a transcription service comprising a first plurality of programming instructions stored in the memory which, when operating on the processor, causes the computing device to:
receive audio data of a call between a customer and a contact center agent;
receive call context information from a contact center;
generate a call transcription by using automatic speech recognition;
link the call context information to the call transcription as context metadata; and
send the call transcription, including both the transcribed conversation and context metadata, to a summarization service; and
the summarization service comprising a second plurality of programming instructions stored in the memory which, when operating on the processor, causes the computing device to:
receive the call transcription, the call transcription comprising a transcribed conversation and context metadata;
use the call transcription and the context metadata as an input prompt for a generative artificial intelligence (GAI) model configured to generate as output a call summary; and
display the call summary on a computing device associated with the contact center agent;
wherein, upon receipt of a request from the call center agent request for a new summary, the summarization service:
uses the call transcription and the context metadata as an input prompt for a second generative artificial intelligence (GAI) model configured to generate as output a new call summary; and
displays the new call summary on the computing device associated with the contact center agent.
2. The system of claim 1 , wherein the context metadata comprises information indicating a first channel of the audio data as being associated with the customer and a second channel of the audio data as being associated with the contact center agent.
3. The system of claim 1 , wherein the GAI model is trained using a plurality of customer conversational data.
4. The system of claim 1 , wherein the call context information is received from a computer telephony integration (CTI) system operated by the contact center.
5. The system of claim 4 , wherein the call context information comprises CTI event information associated with the call between the customer and the contact center agent.
6. The system of claim 1 , wherein the agent request for a new summary comprises one or more configuration modifications; and
wherein the one or more configuration modifications changes aspects of the input prompt.
7. The system of claim 6 , wherein the summarization service is further configured to:
receive the agent request for a new summary;
use the call transcription, the context metadata, and configuration modifications as a modified input prompt for the GAI model configured to generate as output a new call summary; and
display the new call summary on the computing device associated with the contact center agent.
8. The system of claim 1 , wherein the contact center agent submits a request for a new call transcription; and
wherein the new call transcription is used by the summarization service to generate the call summary.
9. A method for transcription and summarization using generative artificial intelligence, comprising the steps of:
receiving audio data of a call between a customer and a contact center agent;
receiving call context information from a contact center;
generating a call transcription by using automatic speech recognition;
linking the call context information to the call transcription as context metadata;
sending the call transcription, including both the transcribed conversation and context metadata, to a summarization service;
receiving the call transcription, the call transcription comprising a transcribed conversation and context metadata;
using the call transcription and the context metadata as an input prompt for a generative artificial intelligence (GAI) model configured to generate as output a call summary; and
displaying the call summary on a computing device associated with the contact center agent;
wherein, upon receipt of a request from the call center agent request for a new summary, the summarization service:
uses the call transcription and the context metadata as an input prompt for a second generative artificial intelligence (GAI) model configured to generate as output a new call summary; and
displays the new call summary on the computing device associated with the contact center agent.
10. The method of claim 9 , wherein the context metadata comprises information indicating a first channel of the audio data as being associated with the customer and a second channel of the audio data as being associated with the contact center agent.
11. The method of claim 9 , wheSteerein the GAI model is trained using a plurality of customer conversational data.
12. The method of claim 9 , wherein the call context information is received from a computer telephony integration (CTI) system operated by the contact center.
13. The method of claim 12 , wherein the call context information comprises CTI event information associated with the call between the customer and the contact center agent.
14. The method of claim 9 , wherein the agent request for a new summary comprises one or more configuration modifications; and
wherein the one or more configuration modifications changes aspects of the input prompt.
15. The method of claim 14 , wherein the summarization service is further configured to:
receive the agent request for a new summary;
use the call transcription, the context metadata, and configuration modifications as a modified input prompt for the GAI model configured to generate as output a new call summary; and
display the new call summary on the computing device associated with the contact center agent.
16. The method of claim 9 , wherein the contact center agent submits a request for a new call transcription; and
wherein the new call transcription is used by the summarization service to generate the call summary.