Combination of real-time analytics and automation

Patent metadata

Field	Value
Publication number	US-11190640-B2
Application number	US-201916407891-A
Country	US
Kind code	B2
Filing date	May 9, 2019
Priority date	May 9, 2019
Publication date	Nov 30, 2021
Grant date	Nov 30, 2021

Abstract

Real-time speech analytics (RTSA) provides maintaining real-time speech conditions, rules, and triggers, and real-time actions and alerts to take. A call between a user and an agent is received at an agent computing device. The call is monitored to detect in the call one of the real-time speech conditions, rules, and triggers. Based on the detection, at least one real-time action and/or alert is initiated.

First claim

What is claimed:

1. A real-time speech analytics (RTSA) system, comprising:
a rules module configured to maintain a plurality of rules pertaining to a voice call between a user computing device and an agent computing device, wherein the agent computing device has virtual agent voice capability, wherein the voice call communicates with the virtual agent voice capability of the agent computing device;
a detection module configured to listen to the voice call according to the plurality of rules and to detect that one of the plurality of rules is triggered as a match or as an event;
an analysis module configured to analyze the match or the event and determine at least one of an action or an alert to perform; and
an action and alerts module configured to receive an instruction from the analysis module pertaining to the at least one of the action or the alert to perform, and configured to perform the at least one of the action or the alert, wherein the at least one of the action or the alert comprises at least one of alerting a human agent via the agent computing device to a condition, or sending an instruction to the human agent via the agent computing device.

2. The RTSA system of claim 1 , wherein the rules module, the detection module, the analysis module, and the action and alerts module are comprised within a computing device.

3. The RTSA system of claim 1 , wherein the plurality of rules dictate the call to be analyzed and how the call is analyzed.

4. The RTSA system of claim 1 , wherein the plurality of rules define a plurality of keywords to detect and sentiment to detect.

5. The RTSA system of claim 1 , wherein the rules module is further configured to at least one of receive, determine, or set the plurality of rules.

6. The RTSA system of claim 1 , wherein the at least one of the action or the alert to perform further comprises at least one of sending an instruction to an output device, or sending an indicator to a desktop and process analytics (DPA) engine.

7. The RTSA system of claim 1 , wherein the at least one of the action or the alert to perform further comprises at least one of providing a knowledge base article or link, alerting a credit check disclosure, alerting a potentially fraudulent transaction, marking a call for follow-up, or alerting to customer churn.

8. A system comprising:
an agent computing device configured to receive a voice call from a user computing device, wherein the agent computing device has virtual agent voice capability, wherein the voice call communicates with the virtual agent voice capability of the agent computing device; and
a computing device comprising:
a real-time speech analytics (RTSA) engine configured to monitor and analyze the voice call in real-time to detect at least one of predetermined words, predetermined phrases, and sentiment, and to guide an interaction during the voice call using one or more automated interventions, wherein the one or more automated interventions comprises performing at least one of an action or an alert, wherein the at least one of the action or the alert comprises at least one of alerting a human agent via the agent computing device to a condition, or sending an instruction to the human agent via the agent computing device.

9. The system of claim 8 , further comprising:
a call recording engine configured to capture the interaction between a user and an agent during the call;
a real-time biometrics engine configured to authenticate the user;
a speech analytics (SA) engine configured to analyze and categorize the call; and
a desktop and process analytics (DPA) engine configured to incorporate desktop events at the agent computing device during the call.

10. The system of claim 8 , further comprising an output device configured to output at least one of the action or the alert generated by the RTSA engine.

11. The system of claim 8 , wherein the RTSA engine comprises:
a rules module configured to at least one of receive, determine, set, or maintain a plurality of rules pertaining to the call;
a detection module configured to listen to the call according to the plurality of rules and to detect that one of the plurality of rules is triggered as a match or as an event;
an analysis module configured to analyze the match or the event and determine at least one of an action or an alert to perform; and
an action and alerts module configured to receive an instruction from the analysis module pertaining to the at least one of the action or the alert to perform, and configured to perform the at least one of the action or the alert.

12. The system of claim 8 , wherein the at least one of an action or an alert to perform further comprises at least one of sending an instruction to an output device, sending an indicator to a desktop and process analytics (DPA) engine, providing a knowledge base article or link, alerting a credit check disclosure, alerting a potentially fraudulent transaction, marking a call for follow-up, or alerting to customer churn.

13. The system of claim 11 , wherein the plurality of rules dictate the call to be analyzed and how the call is analyzed, and wherein the plurality of rules define a plurality of keywords to detect and sentiment to detect.

14. A method comprising:
maintaining, at a detection module, a plurality of real-time speech conditions, rules, and triggers;
maintaining, at an analysis module, a plurality of real-time actions and alerts to take;
receiving a voice call at an agent computing device, wherein the agent computing device has virtual agent voice capability, wherein the voice call communicates with the virtual agent voice capability of the agent computing device;
detecting in the voice call one of the plurality of real-time speech conditions, rules, and triggers; and
initiating one or more of the plurality of real-time actions and alerts based on the detected one of the plurality of real-time speech conditions, rules, and triggers, wherein the one or more of the plurality of real-time actions and alerts comprises at least one of alerting a human agent via the agent computing device to a condition, or sending an instruction to the human agent via the agent computing device.

15. The method of claim 14 , further comprising maintaining a plurality of recording rules pertaining to a call at a rules module, and implementing the plurality of recording rules on the call.

16. The method of claim 14 , wherein the plurality of real-time speech conditions, rules, and triggers comprises at least one of predetermined words, predetermined phrases, and sentiment, to detect during the call.

17. The method of claim 14 , wherein the plurality of real-time actions and alerts further comprises at least one of sending an instruction to an output device, sending an indicator to a desktop and process analytics (DPA) engine, providing a knowledge base article or link, alerting a credit check disclosure, alerting a potentially fraudulent transaction, marking a call for follow-up, or alerting to customer churn.

Assignees

• Verint Americas Inc

Inventors

• Singer David Warren
• Spohrer Daniel Thomas
• Calahan Marc Adam
• Munro Paul Michael
• Duke Gary Andrew
• Carberry Padraig
• Schnurr Christopher Jerome

Classifications

• H04M2203/401

  Performance feedback · CPC title

• H04M2201/40

  using speech recognition · CPC title

• H04M3/5175 Primary

  Call or contact centers supervision arrangements · CPC title

• H04M3/42221

  Conversation recording systems (at the subscriber's set H04M1/656) · CPC title

• G10L2015/227

  of the speaker; Human-factor methodology · CPC title