SYSTEM, METHOD AND APPARATUS FOR CONVERSATIONAL GUIDANCE
The present disclosure provides real-time, contextually appropriate behavioral guidance by utilizing machine learning models applied in real-time to call audio data. The systems and methods disclosed herein use a combination of acoustic signal processing and automatic speech recognition to convert raw call audio into features that are utilized in the machine learning models to create usable outputs to provide a user with behavioral guidance within a given context of a call or interaction with a customer in real-time.
1 . A computer-implemented method for outputting feedback to a user, the method comprising:
using at least one hardware processor for extracting code for:
acquiring verbal data from a first party during a communication session, the acquired verbal data based, at least in part, on content of the communication session;
acquiring non-verbal data from the first party during the communication session, the acquired non-verbal data based, at least in part, on one or more behaviors exhibited by the first party during the communication session;
accessing one or more models from an electronic memory device;
generating feedback data based, at least in part, on the one or more accessed models, the acquired verbal data and the acquired non-verbal data; and
outputting the feedback data to a user device, the feedback data utilized by one or more users to affect the communication session during the communication session.
2 . The computer-implemented method for outputting feedback to a user, as claimed in claim 1 , wherein acquiring non-verbal data includes acquiring behavioral data, based, at least in part, on acoustic signal processing and behavioral model program data.
3 . The computer-implemented method for outputting feedback to a user, as claimed in claim 1 , wherein generating feedback data is based, at least in part, on context model program data.
4 . The computer-implemented method for outputting feedback to a user, as claimed in claim 1 , wherein generating feedback data is based, at least in part, on call type model program data.
5 . The computer-implemented method for outputting feedback to a user, as claimed in claim 1 , wherein generating feedback data is based, at least in part, on topic detection model program data.
6 . The computer-implemented method for outputting feedback to a user, as claimed in claim 1 , wherein generating feedback data is based, at least in part, on call score model program data.
7 . The computer-implemented method for outputting feedback to a user, as claimed in claim 1 , wherein outputting the feedback data to the user device is at a remote location.
8 . The computer-implemented method for outputting feedback to a user, as claimed in claim 1 , wherein the feedback data is utilized by one or more users to affect subsequent communication sessions.
9 . The computer-implemented method for outputting feedback to a user, as claimed in claim 1 , wherein generating feedback data is based, at least in part, on segmentation.
10 . The computer-implemented method for outputting feedback to a user, as claimed in claim 1 , wherein acquiring non-verbal data is acquired independent of a model.
11 . The computer-implemented method for outputting feedback to a user, as claimed in claim 1 , wherein generating feedback data is based, at least in part, on one or more determined time intervals associated with acquiring verbal data.
12 . The computer-implemented method for outputting feedback to a user, as claimed in claim 1 , wherein generating feedback data is based, at least in part, on a first time interval associated with acquiring verbal data and a second time interval associated with acquiring verbal data, the second time interval being after the first time interval.
13 . A computer-implemented method for outputting feedback to a user, the method comprising:
acquiring verbal data from a first party during a communication session, the acquired verbal data based, at least in part, on content of the communication session;
acquiring non-verbal data from the first party during the communication session, the acquired non-verbal data based, at least in part, on one or more behaviors exhibited by the first party during the communication session;
accessing one or more models from an electronic memory device;
generating feedback data based, at least in part, on the one or more accessed models, the acquired verbal data and the acquired non-verbal data; and
outputting the feedback data to a user device, the feedback data utilized by one or more users to affect the communication session during the communication session.
14 . A system for outputting feedback to a user, comprising:
one or more memories configured to store representations of data in an electronic form; and
one or more processors, operatively coupled to one or more of the memories, the processors configured to access the data and process the data to:
acquire verbal data from a first party during a communication session, the acquired verbal data based, at least in part, on content of the communication session,
acquire non-verbal data from the first party during the communication session, the acquired non-verbal data based, at least in part, on one or more behaviors exhibited by the first party during the communication session,
access one or more models from an electronic memory device,
generate feedback data based, at least in part, on the one or more accessed models, the acquired verbal data and the acquired non-verbal data, and
output the feedback data to a user device, the feedback data utilized by one or more users to affect the communication session during the communication session.
15 . The system for outputting feedback to a user, as claimed in claim 14 , where the acquired non-verbal data includes behavioral data, based, at least in part, on acoustic signal processing and behavioral model program data.
16 . The system for outputting feedback to a user, as claimed in claim 14 , where the feedback data is based, at least in part, on one or more model data.
17 . The system for outputting feedback to a user, as claimed in claim 14 , where the feedback data is based, at least in part, on one or more determined time intervals associated with the acquired verbal data.
18 . The system for outputting feedback to a user, as claimed in claim 14 , where the feedback data is based, at least in part, on a first time interval associated with the acquired verbal data and a second time interval associated with the acquired verbal data, the second time interval being after the first time interval.
19 . The system for outputting feedback to a user, as claimed in claim 14 , where the feedback data utilized by one or more users to affect subsequent communication sessions.
20 . The system for outputting feedback to a user, as claimed in claim 14 , where the feedback data is based, at least in part, on segmentation.