System for Dynamic Management of Customer Direction During Live Interaction

• US 20090210228A1
• Filed: 02/15/2008
• Published: 08/20/2009
• Est. Priority Date: 02/15/2008
• Status: Active Grant

• Current Assignee: Astute, Inc. (Astute Holdings, Inc.)
• Original Assignee: Astute Innovations, Inc.
• Inventors: George, Alex K.
• Granted Patent: US 8,706,498 B2
• Time in Patent Office: Days
• US Class Current: 704/251
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2203/2011 Service processing based on information specified by a party before or during a call, e.g. information, tone or routing selection
• CPC Class Codes: H04M 2203/357 Autocues for dialog assistance
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends

Abstract

A system for customer interaction includes a telephony-enabled device for receiving voice calls from customers, a voice recognition engine connected to the telephony-enabled device for monitoring the voice channel, and an application server connected to the voice recognition engine for receiving notification when specific keywords phrases or tones are detected. The system is characterized in that the application server selects scripts for presentation to the customer based at least in part on the notifications received from the voice recognition engine.

Claims

1. A system for customer interaction comprising:

a telephony-enabled device for receiving voice calls from customers;

a voice recognition engine connected to the telephony-enabled device for monitoring the voice channel; and

an application server connected to the voice recognition engine for receiving notification when specific keywords phrases or tones are detected;

characterized in that the application server selects scripts for presentation to the customer based at least in part on the notifications received from the voice recognition engine.

2. A method for selecting from a pool of scripts a script to send to an agent interacting with a customer comprising the steps:

(a) providing a grammar library of keywords and/or phrases, a scale defining voice tone levels, and scripts;

(b) associating one or more of the keywords and/or phrases to individual ones of the scripts;

(c) monitoring the voice channel using voice recognition;

(d) recognizing one or more keywords and/or phrases spoken, or a voice tone level; and

(e) selecting a script and serving the script to the agent based at least in part on the results of step (d) weighed against one or more rules.

3. A system for altering a generic script served to an agent during live interaction with a customer comprising:

a telephony-enabled device for receiving voice calls from customers;

a voice recognition engine connected to the telephony-enabled device for monitoring the voice channel; and

an application server connected to the voice recognition engine for receiving notification when specific keywords phrases or tones are detected;

characterized in that the application server selects and serves descriptive text related to a product or service into the existing script based at least in part on the notifications received from the voice recognition engine.

4. A system for alerting a supervisor to monitor a voice interaction between an agent and a customer comprising:

a telephony-enabled device for receiving voice calls from customers;

a voice recognition engine connected to the telephony-enabled device for monitoring the voice channel; and

an application server connected to the voice recognition engine for receiving notification when specific keywords phrases or tones are detected;

characterized in that the application server serves an alert to monitor the call to a supervisor based at least in part on the notifications received from the voice recognition engine.

5. A method for determining when to send notification to a supervisor to monitor a live interaction between an agent and a customer comprising the steps:

(a) providing a grammar library of keywords and/or phrases and a scale defining voice tone levels;

(b) associating one or more of the voice tone levels, keywords, and/or phrases to a notification event to monitor an interaction;

(c) monitoring the voice channel using voice recognition;

(d) recognizing one or more keywords and/or phrases spoken, or a voice tone level; and

(e) sending notification to monitor the interaction based at least in part on the results of step (d) weighed against one or more rules.