System for and method of automated quality monitoring

• US 8,050,921 B2
• Filed: 07/02/2009
• Issued: 11/01/2011
• Est. Priority Date: 08/22/2003
• Status: Active Grant

• Current Assignee: inContact Incorporated (Nice Ltd)
• Original Assignee: Siemens Enterprise Communications, Inc. (Atos SE)
• Inventors: Mark, Lawrence, Giordano, Geoffrey J., Scarano, Robert, Lambert, Kori
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US12/496,940
• Publication Number:
  US 20090306984A1
• Time in Patent Office: 852 Days
• Field of Search: 704/246, 704/251, 379/88.13, 707/5, 707/6
• US Class Current: 704/246
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

A system and method according to the present invention automates call monitoring activities to evaluate and directly improve agent-customer interactions. Rather than listening to an entire call or monitoring only a small fraction of all the calls made in the contact center, the system performs highly accurate, automated evaluations of all customer interactions. By automating the time-consuming aspect of monitoring calls, the system empowers contact center operators to address quality issues, more accurately measure, coach and reward agents, and identify business-critical trends.

Claims

1. A system for monitoring a spoken language message comprising:

an interface operational to capture the spoken language message;

a speech processor including a parser operational to implement a search expression syntax to decode a search expression into a number of target search words and target search phrases;

a rules processor that is operational to define rules defining the target search words and the target search phrases and relationships between the target search words and the target search phrases, the rules processor communicatively connected to the speech processor to communicate the rules to the speech processor; and

a speech engine operational to search the spoken language message for one or more of said target search words and said target search phrases and, in response, provide search results identifying a location of any candidate utterances matching said target search words and said target search phrases together with confidence values indicating a certainty of each of the candidate utterances corresponding to ones of said target search words and said target search phrases; and

said speech engine calculating the confidence values by taking into account locations within the spoken language message in which the target search words and target search phrases are found such that a target search word or target search phrase found where expected is given a higher confidence value relative to a target search word or target search phrase found in an unexpected location within the spoken language message, wherein expected locations for the target search words and target search phrases are at least partially defined by a predefined script; and

said speech processor responsive to said search expression for identifying one or more of said target search phrases and said target search words to said speech engine and analyzing said search results to determine whether a condition specified by said search expression is satisfied.

2. The system according to claim 1, wherein said parser includes logic for decoding a plurality of symbols into corresponding operators defining said relationships specified by said rules.

3. The system according to claim 1, wherein said parser recognizes a plurality of operators defining said rules, said operators selected form the set consisting of logical AND, logical OR, unitary negation, permutations, proximity and confidence.

4. The system of claim 1 wherein the amount of time between at least one of the target search phrases and the target search words in the spoken language message is also utilized to deterinine the confidence values.

5. The system of claim 4 wherein the amount of time is a predefined amount of time.

6. The system of claim 4 wherein the predefined script fully defines the expected locations for the target search words and target search phrases.

7. The system of claim 1 wherein the predefined script fully defines the expected locations for the target search words and target search phrases.

8. A method of monitoring a spoken language message comprising the steps of:

capturing the spoken language message;

defining rules that define target search phrases and target search words and relationships between the target search phrases and target search words;

a parser parsing a search expression to implement a search expression syntax and to decode said search expression into a number of the target search phrases and the target search words;

searching the spoken language message for said target search words and said target search phrases;

providing search results identifying a location of any candidate utterances matching the target search phrases together with confidence values indicating a certainty of each of the candidate utterances to corresponding ones of said target search phrases;

calculating the confidence values by taking into account locations within the spoken language message in which the target search words and target search phrases are found such that a target search word or target search phrase found where expected is given a higher confidence value relative to a target search word or target search phrase found in an unexpected location within the spoken language message, wherein expected locations for the target search words and target search phrases are at least partially defined by a predefined script; and

a system for monitoring and analyzing the spoken message analyzing said search results to determine whether a condition specified by said search expression is satisfied.

9. The method according to claim 8, further comprising a step of decoding a plurality of symbols into corresponding operators defining the relationships specified by said rules.

10. The method according to claim 8, further comprising a step of recognizing a plurality of operators defining said rules, said operators selected form the set consisting of logical AND, logical OR, unitary negation, permutations, proximity and confidence.

11. A call center comprising:

a system for monitoring and analyzing calls received by the call center, the system comprising;

an interface operational to capture a spoken language message;

a speech processor including a parser operational to implement a search expression syntax to decode a search expression into a number of target search words and target search phrases; and

a rules processor that is operational to define rules defining the target search words and the target search phrases and relationships between the target search words and the target search phrases, the rules processor communicatively connected to the speech processor to communicate the rules to the speech processor; and

a speech engine operational to search the spoken language message for one or more of said target search words and said target search phrases and, in response, provide search results identifying a location of any candidate utterances matching said target search words and said target search phrases together with confidence values indicating a certainty of each of the candidate utterances corresponding to ones of said target search words and said target search phrases; and

said speech engine calculating the confidence values by taking into account locations within the spoken language message in which the target search words and target search phrases are found such that a target search word or target search phrase found where expected is given a higher confidence value relative to a target search word or target search phrase found in an unexpected location within the spoken language message, wherein expected locations for the target search words and target search phrases are at least partially defined by a predefined script; and

said speech processor responsive to said search expression for identifying one or more of said target search phrases and said target search words to said speech engine and analyzing said search results to determine whether a condition specified by said search expression is satisfied.

12. The system of claim 11 wherein the amount of time between at least one of the target search phrases and the target search words in the spoken language message is also utilized to determine the confidence values.

13. The system of claim 12 wherein the amount of time is a predefined amount of time.