Artificial intelligence based setting of controls in a user interface

1 . A system for artificial intelligence-based evaluation of an agent interaction, comprising:

a processor;

a data store storing a voice session recording of a call and an evaluation form;

a visual display for displaying the evaluation form, wherein the evaluation form comprises an evaluation question and an answer control settable to indicate an answer to the evaluation question;

a non-transitory computer readable medium storing instructions executable by the processor to:

generate, using a speech-to-text transcription server, a transcript of the voice session recording of the call;

parse the evaluation form to identify the evaluation question for an intended call participant interaction;

automatically determine, using a large language model, whether the intended call participant interaction of the evaluation question is present in the transcript, wherein automatically determining whether the intended call participate interaction is present in the transcript comprises:

generating a prompt to the large language model to cause the large language model to evaluate text from the transcript to determine if the intended call participant interaction is present in the transcript and send the prompt with text from the transcript; and

processing the prompt and text from the transcript with the large language model to determine whether the intended call participate interaction is present in the transcript; and

when the intended call participant interaction is determined using the large language model to be present in the transcript:

record a first answer determined using the large language model for the evaluation question corresponding to the voice session recording, the first answer indicating a presence of the intended call participant interaction in the voice session recording; and

based on the first answer, automatically set the answer control to a first setting prior to serving the evaluation form for display in the visual display to cause the evaluation form when displayed in the visual display to indicate the presence of the intended call participant interaction in the voice session recording.

2 . The system of claim 1 , wherein the instructions are further executable by the processor to:

when the intended call participant interaction is determined not to be present in the voice session recording:

record a second answer determined by the large language model as the response to the evaluation question for the voice session recording, the second answer indicating the intended call participant interaction is not present in the call; and

automatically set the answer control of the evaluation form to a second setting, the second setting indicating that the intended call participant interaction is not present in the voice session recording.

3 . The system of claim 1 , wherein the instructions are further executable by the processor to:

receive a verification answer to the evaluation question;

determine that the verification answer differs from the response to the evaluation question; and

update the large language model with the evaluation question and the verification answer.

4 . The system of claim 1 , wherein the evaluation question is in a Boolean format.

5 . A computer program product comprising a non-transitory computer readable medium storing instructions executable by a processor to:

store a voice session recording of a call and an evaluation form;

display, on a visual display, the evaluation form, wherein the evaluation form comprises an evaluation question and an answer control settable to indicate an answer to the evaluation question;

generate, using a speech-to-text transcription server, a transcript of the voice session recording of the call;

parse the evaluation form to identify the evaluation question for an intended call participant interaction;

automatically determine, using a large language model, whether the intended call participant interaction of the evaluation question is present in the transcript, wherein automatically determining whether the intended call participate interaction is present in the transcript comprises:

generating a prompt to the large language model to cause the large language model to evaluate text from the transcript to determine if the intended call participant interaction is present in the transcript and send the prompt with text from the transcript; and

processing the prompt and text from the transcript with the large language model to determine whether the intended call participate interaction is present in the transcript; and

when the intended call participant interaction is determined using the large language model to be present in the transcript:

record a first answer determined using the large language model for the evaluation question corresponding to the voice session recording, the first answer indicating a presence of the intended call participant interaction in the voice session recording; and

based on the first answer, automatically set the answer control to a first setting in the evaluation form prior to serving the evaluation form for display in the visual display to cause the evaluation form when displayed in the visual display to indicate the presence of the intended call participant interaction in the voice session recording.

6 . The computer program product of claim 5 , wherein the instructions are further executable by the processor to:

when the intended call participant interaction is determined using the large language model not be present in the voice session recording, automatically set the answer control for the evaluation question to a second setting to indicate that the intended call participant interaction is not present in the voice session recording.

7 . The computer program product of claim 5 , wherein the instructions are further executable by the processor to:

receive a verification answer to the evaluation question;

determine that the verification answer differs from the response to the evaluation question; and

update the large language model with the evaluation question and the verification answer.

8 . The computer program product of claim 5 , wherein the evaluation question is in a Boolean format.

9 . The computer program product of claim 5 , wherein the answer control comprises a radio button.

10 . A method for artificial intelligence-based evaluation of an agent interaction comprising:

storing a voice session recording of a call and an evaluation form, wherein the voice session recording comprises a plurality of call participant interactions recorded by a call center recording system;

displaying, on an evaluation operator interface, an evaluation question from the evaluation form and an answer control settable to indicate a response to the evaluation question;

generate, using a speech-to-text transcription server, a transcript of the voice session recording of the call;

parse the evaluation form to identify the evaluation question for an intended call participant interaction;

automatically determine, using a large language model, that the intended call participant interaction of the evaluation question is present in the transcript, wherein automatically determining that the intended call participate interaction is present in the transcript comprises:

generating a prompt to the large language model to cause the large language model to evaluate text from the transcript to determine if the intended call participant interaction is present in the transcript and send the prompt with text from the transcript; and

processing the prompt and text from the transcript with the large language model to determine that the intended call participate interaction is present in the transcript; and

when the intended call participant interaction is present in the transcript:

recording a first answer generated using large language model for the evaluation question corresponding to the voice session recording, the first answer indicating a presence of the intended call participant interaction in the voice session recording; and

based on the first answer, automatically setting the answer control in the evaluation from to a first setting prior to serving the evaluation form for display in the visual display to cause the evaluation form when displayed in the visual display to indicate the presence of the intended call participant interaction in the voice session recording.

11 . The method of claim 10 , wherein the first answer is one of a plurality of selectable settings and indicates the presence of the intended call participant interaction in the voice session recording.

12 . The method of claim 11 , further comprising:

receiving a verification answer to the evaluation question;

determining that the verification answer differs from the response to the evaluation question; and

updating the machine learning model with the evaluation question and the verification answer.

13 . The method of claim 10 , wherein the second answer is one of a plurality of selectable settings and indicates that the intended call participant interaction is not present in the voice session recording.

14 . The method of claim 10 , wherein the machine learning model is a large language model (LLM).

15 . The method of claim 10 , wherein submitting the voice session recording to the machine learning model comprises submitting a transcript of the call to the machine learning model.

16 . The method of claim 11 , wherein the evaluation question is in a Boolean format.