AUTOMATED QUALITY METRIC MODELS BASED ON CUSTOMER DATA
Systems and methods for automating quality metrics are provided. Transcripts of interactions with agents and assigned quality metrics for a variety of questions are collected for an entity. The quality metrics may relate to questions such as “Did the agent greet the customer with a friendly greeting?” and “Did the agent answer the customer's question after returning from the hold?”. For each question used by the entity to generate quality metrics, a large language model or classifier is trained for the question using the transcripts and the assigned quality metrics for the question. The transcripts may be processed to include textual information corresponding to metadata associated with the communications such as time stamps for call holds, utterances, and silent periods. The trained large language model or classifiers may then be used later to automatically assign quality metrics to current interactions for their corresponding question.
1 . A method for automating quality metrics comprising:
receiving an evaluation including at least one question of a plurality of questions and interaction data representing a current interaction by a computing device;
generating a quality metric for the at least one question for the current interaction using a first large language model or a first classifier and the interaction data representing the current interaction by the computing device; and
associating the quality metric for the at least one question with the current interaction by the computing device.
2 . The method of claim 1 , further comprising:
receiving interaction data representing previous interactions with one or more agents by the computing device, wherein each interaction is associated with a question of the plurality of questions and a quality metric;
using a first portion of the interaction data representing the previous interactions, training the first large language model or the first classifier by the computing device.
3 . The method of claim 2 , further comprising:
using a second portion of the interaction data representing the previous interactions, generating performance indicators for the first classifier and the first large language model; and
generating the quality metric for the question for the current interaction using one of the first large language model or the first classifier based on the performance indicators.
4 . The method of claim 3 , further comprising:
using the second portion of the interaction data, generating performance indicators for a second large language model or a second classifier, wherein the second large language model is not trained using the interaction data and the second classifier is not trained using the first interaction data; and
generating the quality metric for the question for the current interaction using one of the first large language model, the second large language model, the first classifier, or the second classifier based on the performance indicators.
5 . The method of claim 4 , further comprising:
determining that the generated performance indicators for the first large language model, the second large language model, the first classifier, and the second classifier all fall below a threshold; and
in response to the determination, generating the quality metric for the question for the current interaction using some combination of the first large language model, the second large language model, the first classifier and the second classifier based on the performance indicators.
6 . The method of claim 5 , wherein the first classifier comprises a neural network classifier, or XGBoost.
7 . The method of claim 1 , wherein the interaction data for a previous interaction comprises a call transcript and metadata, and further comprising:
mapping the metadata to text; and
combining the text with the call transcript.
8 . A system for automating quality metrics comprising:
a computing device; and
a computer-readable medium with computer-executable instructions stored thereon that when executed by the computing device cause the computing device to:
receive an evaluation including at least one question of a plurality of questions and interaction data representing a current interaction;
generate a quality metric for the at least one question for the current interaction using a first large language mode or a first classifier and the interaction data representing the current interaction; and
associate the quality metric for the at least one question with the current interaction.
9 . The system of claim 8 , further comprising computer-executable instructions that when executed by the computing device cause the computing device to:
receive interaction data representing previous interactions with one or more agents by the computing device, wherein each interaction is associated with a question of the plurality of questions and a quality metric;
use a first portion of the interaction data representing the previous interactions, training the first large language model or the first classifier.
10 . The system of claim 9 , further comprising computer-executable instructions that when executed by the computing device cause the computing device to:
using a second portion of the interaction data representing the previous interactions, generate performance indicators for the first classifier and the first large language model; and
generate the quality metric for the question for the current interaction using one of the first large language model or the first classifier based on the performance indicators.
11 . The system of claim 10 , further comprising computer-executable instructions that when executed by the computing device cause the computing device to:
use the second portion of the interaction data, generating performance indicators for a second large language model or a second classifier, wherein the second large language model is not trained using the interaction data and the second classifier is not trained using the first interaction data; and
generate the quality metric for the question for the current interaction using one of the first large language model, the second large language model, the first classifier, or the second classifier based on the performance indicators.
12 . The system of claim 11 , further comprising computer-executable instructions that when executed by the computing device cause the computing device to:
determine that the generated performance indicators for the first large language model, the second large language model, the first classifier, and the second classifier all fall below a threshold; and
in response to the determination, generate the quality metric for the question for the current interaction using some combination of the first large language model, the second large language model, the first classifier, and the second classifier based on the performance indicators.
13 . The system of claim 12 , wherein the first classifier comprises a neural network classifier, or XGBoost.
14 . The system of claim 8 , wherein the interaction data for a previous interaction comprises a call transcript and metadata, and further comprising computer-executable instructions that when executed by the computing device cause the computing device to:
map the metadata to text; and
combine the text with the call transcript.
15 . A non-transitory computer-readable medium with computer-executable instructions stored thereon that when executed by a computing device cause the computing device to:
receive an evaluation including at least one question of a plurality of questions and interaction data representing a current interaction;
generate a quality metric for the at least one question for the current interaction using a first large language model or a first classifier and the interaction data representing the current interaction; and
associate the quality metric for the at least one question with the current interaction.
16 . The computer-readable medium of claim 15 , further comprising computer-executable instructions that when executed by the computing device cause the computing device to:
receive interaction data representing previous interactions with one or more agents by the computing device, wherein each interaction is associated with a question of the plurality of questions and a quality metric;
use a first portion of the interaction data representing the previous interactions, training the first large language model or the first classifier.
17 . The computer-readable medium of claim 16 , further comprising computer-executable instructions that when executed by the computing device cause the computing device to:
using a second portion of the interaction data representing the previous interactions, generate performance indicators for the first classifier and the first large language model; and
generate the quality metric for the question for the current interaction using one of the first large language model or the first classifier based on the performance indicators.
18 . The computer-readable medium of claim 17 , further comprising computer-executable instructions that when executed by the computing device cause the computing device to:
use the second portion of the interaction data, generating performance indicators for a second large language model or a second classifier, wherein the second large language model is not trained using the interaction data and the second classifier is not trained using the first interaction data; and
generate the quality metric for the question for the current interaction using one of the first large language model, the second large language model, the first classifier, or the second classifier based on the performance indicators.
19 . The computer-readable medium of claim 18 , further comprising computer-executable instructions that when executed by the computing device cause the computing device to:
determine that the generated performance indicators for the first large language model, the second large language model, the first classifier, and the second classifier all fall below a threshold; and
in response to the determination, generate the quality metric for the question for the current interaction using some combination of the first large language model, the first classifier, the second large language model, and the second classifier based on the performance indicators.
20 . The computer-readable medium of claim 15 , wherein the interaction data for a previous interaction comprises a call transcript and metadata, and further comprising computer-executable instructions that when executed by the computing device cause the computing device to:
map the metadata to text; and
combine the text with the call transcript.