System for dynamic management of customer direction during live interaction

• US 8,706,498 B2
• Filed: 02/15/2008
• Issued: 04/22/2014
• Est. Priority Date: 02/15/2008
• Status: Active Grant

• Current Assignee: Astute, Inc. (Astute Holdings, Inc.)
• Original Assignee: Astute, Inc. (Astute Holdings, Inc.)
• Inventors: George, Alex K.
• Primary Examiner(s): He, Jialong
• Application Number:
  US12/032,338
• Publication Number:
  US 20090210228A1
• Time in Patent Office: 2,258 Days
• Field of Search: 379/265.06, 704/270, 704/270.1
• US Class Current: 704/270
• 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 customer contact center system for facilitating live voice interaction between a customer and a contact center agent, comprising:

a telephony-enabled device configured to receive voice calls from customers;

a voice recognition engine connected to the telephony-enabled device and configured to monitor a voice channel;

a library of scripts which represent offers for a product or service;

a customer relations management server comprising customer information for a plurality of customers; and

an application server connected to the voice recognition engine and the customer relations management server, said application server comprising an offer engine;

wherein the offer engine is configured to

select a script representing an offer for a product or service from said library based upon customer information provided by said customer relations management server in combination with a detection of one or more of keywords, phrases, tones or combinations thereof on the voice channel,

deliver the selected script to the agent such that the agent may read the script to the customer, and

upon detection by the voice recognition engine on the voice channel of one or more keywords, phrases, voice tones or combination thereof indicative of the customer'"'"'s reaction to the offer represented by the script, modify the script or select and deliver a new script such that the modified or new script may be read by the agent, wherein the modified or new script represents a new offer for a product or service.

2. The customer contact center system of claim 1, further comprising a rules database wherein the offer engine is configured to consult the rules database in order to determine whether or not to select and deliver to an agent a script from said library of scripts, said rules database defining when a script should be selected, which script should be selected for delivery to an agent, and when a script should be modified or a new script selected.

3. The customer contact center system of claim 2, wherein the application server is further configured to send an alert to a supervisor that a live interaction between a customer and an agent should be monitored based upon a detection of one or more keywords, phrases, tones or combination thereof on the voice channel.

4. The customer contact center system of claim 1, wherein one or more of the scripts in said library comprise template scripts which include text placeholders, and further wherein said offer engine is configured such that, upon detection of one or more keywords, phrases, voice tones or combination thereof by the voice recognition engine in response to the reading of the template script by the agent, the offer engine causes text to be inserted into one or more of said text placeholders such that a modified script may be read by the agent.

5. A computer-implemented method for facilitating live voice interaction between a customer and a contact center agent comprising the steps:

(a) monitoring a voice channel of a conversation between a customer and a contact center agent using a voice recognition engine;

(b) upon detection of one or more keywords, phrases, voice tones, or combination thereof by the voice recognition engine, consulting a rules database, by an offer engine, to determine whether or not the detected keywords, phrases or voice tones trigger the selection of a pre-written script from a library of scripts, wherein said scripts represent offers for a product or service;

(c) serving a pre-written script selected in step (b) to the agent such that the agent may read the script to the customer;

(d) continuing to monitor the voice channel;

(e) upon detection of one or more keywords, phrases, voice tones or combination thereof by the voice recognition engine indicative of the customer'"'"'s reaction to the offer represented by the script, consulting the rules database, by the offer engine, to determine whether or not the detected keywords, phrases or voice tones trigger modification of the previously selected script or the selection of a new pre-written script;

(f) modifying the script served in step (c) or serving a new script to the agent, as determined in step (e), such that the agent may read the modified or new script to the customer, wherein the modified or new script represents a new offer for a product or service; and

(g) repeating steps (d)-(f) while the customer and agent are engaged in live interaction;

wherein steps (b)-(c) and (e)-(f) are performed by an application server.

6. The method of claim 5, further comprising the steps of:

consulting a rules database to determine whether or not detected keywords, phrases, voice tones, or combination thereof trigger notification of a supervisor; and

upon a determination that detected keywords, phrases or voice tones trigger notification, sending an alert to a supervisor that the live interaction between the customer and agent should be monitored.