System method and apparatus for combining words and behaviors
AssigneeVerint Americas Inc.
InventorJohn Kane
Life of this patent
Estimating the term…
Abstract
A system and method for integrating audio data collected, such as audio data and analytical data, to perform behavioral analysis on the audio data, using an application of acoustic signal processing and machine learning algorithms, by converting the audio data to text data and performing behavioral analysis on the text data. The behavioral analysis data from the audio application of acoustic signal processing is combined with machine learning algorithms and speech to text data to provide a call agent with feedback to assist in the next best action or insight into customer behaviors.
Claims20
A computer-implemented method for outputting feedback data to a selected device, the method comprising:
- using at least one hardware processor for extracting code for:
- accessing audio data from a communication session between a caller and an agent;
- generating behavioral data by performing behavioral analysis of at least a portion of the audio data, the behavioral analysis including acoustic signal processing of the portion of audio data and applying one or more machine learning algorithms to the portion of the audio data;
- generating text data by converting at least a portion of the audio data to text data;
- analyzing the text data using natural language processing;
- generating integrated data by combining the behavioral data with the analyzed text data;
- accessing rules of a set of rules;
- comparing the integrated data to the rules;
- generating feedback data based on the comparison;
- and
- outputting the feedback data to the selected device during the communication session between the caller and the agent.
A system for outputting feedback data to a selected device, 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:
- access audio data from a communication session between a caller and an agent;
- generate behavioral data by performing behavioral analysis of at least a portion of the audio data, the behavioral analysis including acoustic signal processing of the portion of audio data and applying one or more machine learning algorithms to the portion of the audio data;
- store the behavioral data;
- generate text data by converting at least a portion of the audio data to text data;
- analyze the text data by applying natural language processing to the text data;
- store the text data;
- combine the stored behavioral data with the stored text data;
- compare the combined behavioral data and the text data to one or more rules;
- generate feedback data based on the comparison;
- and
- output the feedback data to the selected device during the communication session between the caller and the agent.
A computer-implemented method for outputting feedback data to a selected device, the method comprising:
- using at least one hardware processor for extracting code for:
- accessing audio data from a communication session between a caller and an agent;
- identifying one or more acoustic portions of the audio data;
- identifying one or more text portions of the acoustic data;
- accessing one or more models;
- combining the one or more acoustic portion of the audio data and the one or more text portions of the audio data using the one or mode models;
- generating feedback data based on the combining;
- and
- outputting the feedback data to the selected device during the communication session between the caller and the agent.
Dependencies are inferred from the claim text.