Script compliance and agent feedback

• US 7,739,115 B1
• Filed: 09/24/2003
• Issued: 06/15/2010
• Est. Priority Date: 02/15/2001
• Status: Expired due to Fees

• Current Assignee: Alorica Incorporated
• Original Assignee: West Corporation
• Inventors: Pettay, Mark J., Vacek, Jill M.
• Primary Examiner(s): Wozniak; James S
• Application Number:
  US10/670,126
• Time in Patent Office: 2,456 Days
• Field of Search: 704/251, 704/275, 704/270.1, 704/270, 704/235, 379/265.06, 705/11
• US Class Current: 704/270
• CPC Class Codes: G10L 15/14 using statistical models, e.g. Hidden Markov Models [HMMs] G10L15/18 takes precedence
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04M 3/5175 Call or contact centers supervision arrangements
• CPC Class Codes: H04M 3/5191 interacting with the Internet

Abstract

Apparatus and methods are provided for using automatic speech recognition to analyze a voice interaction and verify compliance of an agent reading a script to a client during the voice interaction. In one aspect of the invention, a communications system includes a user interface, a communications network, and a call center having an automatic speech recognition component. In other aspects of the invention, a script compliance method includes the steps of conducting a voice interaction between an agent and a client and evaluating the voice interaction with an automatic speech recognition component adapted to analyze the voice interaction and determine whether the agent has adequately followed the script. In yet still further aspects of the invention, feedback in the form of voice records of portions of interactions that the agent handled deficiently, voice records containing recommended improvements to such interactions, as well as supplemental information can be transmitted to the agent.

Claims

1. A method for evaluating compliance of at least one agent reading at least one script to at least one client, the method comprising at least the following:

conducting at least one voice interaction between the at least one agent and the at least one client, wherein the at least one agent follows the at least one script via at least one of a plurality of panels;

entering information by the at least one agent according to responses obtained from the at least one client during the voice interaction;

assigning a time displacement timestamp to each of the plurality of panels as they are presented and viewed by the at least one agent during the voice interaction;

logging a time displacement, based on the time displacement timestamp, per panel as a portion of a log record;

logging the voice interaction as a portion of the log record;

based on the logging, evaluating the at least one voice interaction via the at least one of the plurality of panels employing panel-by-panel playback with the assigned time displacement timestamp with at least one automatic speech recognition component adapted to analyze the at least one voice interaction; and

determining, via generating a score using confidence level thresholds of the least one automatic speech recognition component such that the confidence level thresholds are assigned to each of the plurality of panels and evaluating the score against a static or a varying standard, whether the at least one agent has adequately followed the at least one script by using the evaluated at least one voice interaction.

2. The method of claim 1, wherein conducting at least one voice interaction includes conducting at least one voice interaction involving a telemarketing agent.

3. The method of claim 1, wherein conducting at least one voice interaction includes conducting at least one voice interaction governed by at least one script that includes text corresponding to at least one offer of at least one of goods and services.

4. The method of claim 1, wherein conducting at least one voice interaction includes conducting the at least one voice interaction at least in part on at least one communications network.

5. The method of claim 1, wherein conducting at least one voice interaction includes conducting the at least one voice interaction at least in part on a publicly switched telephone network (PSTN).

6. The method of claim 1, wherein conducting at least one voice interaction includes conducting the at least one voice interaction at least in part on at least one Internet.

7. The method of claim 1, wherein conducting at least one voice interaction includes conducting the at least one voice interaction at least in part on at least one communications network having at least one wireless component.

8. The method of claim 1, wherein conducting at least one voice interaction includes conducting at least one telephone call.

9. The method of claim 1, wherein conducting at least one voice interaction includes conducting at least one telephone call that is initiated by the at least one client.

10. The method of claim 1, wherein conducting at least one voice interaction includes conducting at least one telephone call that is initiated by an entity other than the at least one client.

11. The script compliance method of claim 1, wherein evaluating the at least one interaction includes at least the following:

providing a script compliance module accessible via a user interface and a communications network, the communications network including an analog or digital telephone, an internet-based network, a wireless network or a selected voice communications supporting network;

converting the at least one voice interaction received via the communications network into at least one digital signal comprising at least one spectral representation of the at least one voice interaction,

comparing the at least one digital signal to at least one reference standard that includes at least one known vocabulary, and

matching the at least one digital signal to at least one of words and phrases contained in the at least one reference standard.

12. The method of claim 11, further comprising performing at least one action based upon at least one result of the evaluating of the at least one voice interaction.

13. The method of claim 12, wherein performing at least one action includes transmitting at least one signal to the at least one agent.

14. The method of claim 12, wherein performing at least one action includes transmitting at least one signal to at least one reviewing authority.

15. The method of claim 12, wherein performing at least one action includes making at least one entry in at least one script compliance incentive system.

16. The method of claim 1, further comprising reviewing at least one determination of whether the at least one agent has adequately followed the at least one script.

17. The method of claim 1, wherein determining whether the at least one agent has adequately followed the at least one script includes defining at least one score assigned by the at least one automatic speech recognition component.

18. The method of claim 1, wherein evaluating the at least one voice interaction includes evaluating at least one of the plurality of panels.

19. The method of claim 18, further comprising assigning a respective score to each one of the panels.

20. The method of claim 1, further comprising comparing data representing an actual duration of at least one interaction, wherein the at least one agent reads at least one script to the at least one client, to data representing an expected duration parameter associated with the at least one interaction.

21. The method of claim 1, further comprising dispositioning at least one interaction, wherein the at least one agent reads at least one script to the at least one client, based at least in part on a comparison of data representing an actual duration of the at least one interaction to data representing an expected duration parameter associated with the at least one interaction.

22. The method of claim 1, wherein determining whether the at least one agent has adequately followed the at least one script includes, at least in part, dispositioning at least one interaction, wherein the at least one agent reads at least one script to the at least one client, based at least in part on a comparison of data representing an actual duration of the at least one interaction to data representing an expected duration parameter associated with the at least one interaction.

23. The method of claim 1, further comprising identifying at least one instance of non-compliance with the script, wherein the agent did not adequately follow the script during at least one given interaction.

24. The method of claim 1, further comprising obtaining a voice record of at least a portion of at least one voice interaction.

25. The method of claim 23, further comprising obtaining at least a portion of a voice record of at least a portion of a suggested interaction that is related to the at least one instance of non-compliance.

26. The method of claim 25, wherein obtaining a voice record includes obtaining at least a portion of a pre-recorded voice record.

27. The method of claim 25, wherein obtaining a voice record includes recording at least a portion of a second interaction as the further voice record after identifying that at least one instance of non-compliance.

28. The method of claim 25, further comprising providing at least the portion of the voice record of the at least one voice interaction and the voice record of the suggested interaction to the agent.

29. The method of claim 25, further comprising converting data representing at least the portion of the voice record of the at least one voice interaction and the voice record of the suggested interaction from a first format to at least a second format.

30. The method of claim 25, further comprising e-mailing data representing at least the portion of the voice records to the agent.

31. The method of claim 23, further comprising directing the agent to remedial materials related to improving performance of the agent.

32. The method of claim 23, further comprising providing the agent with data representing at least one aspect in which the agent'"'"'s handling of at least one interaction was deficient.

33. The method of claim 23, further comprising providing the agent with a screen shot representation of at least one aspect in which the agent'"'"'s handling of at least one interaction was deficient.

34. A system for evaluating compliance of at least one agent reading at least one script to at least one client, the system comprising at least the following:

at least one communication network adapted to support at least one voice interaction between the at least one agent and the at least one client, wherein the at least one agent follows at least one script via at least one of a plurality of panels;

at least one information entering component adapted to permit the at least one agent to enter information according to responses obtained from the at least one client during the voice interaction;

a time displacement timestamp component adapted to assign a time displacement timestamp to each of the plurality of panels as they are presented and viewed by the at least one agent during the voice interaction;

a logging component adapted to log a time displacement, based on the time displacement timestamp, per panel as a portion of a log record and log the voice interaction as a portion of the log record;

at least one automatic speech recognition component adapted to analyze, based on the logging component, the at least one voice interaction using each of the plurality of panels employing panel-by-panel playback including the time displacement timestamp and to determine, via generating a score using confidence level thresholds of the at least one automatic speech recognition component such that the confidence level thresholds are assigned to each of the plurality of panels and evaluating the score against a static or a varying standard of the least one automatic speech recognition component, whether the at least one agent has adequately followed the at least one script; and

means for causing at least one action to be taken based upon a determination by the at least one automatic speech recognition component as to whether the at least one agent has adequately followed the at least one script.

35. The system of claim 34, wherein the at least one communication network comprises at least one long distance telephone network.

36. The system of claim 34, wherein the at least one communication network comprises at least one internet-based network.

37. The system of claim 34, further comprising at least one call center that includes a plurality of agent workstations.

38. The system of claim 34, wherein at least one of the agent workstations includes at least a telephone and a computer terminal.

39. The system of claim 34, wherein said agent is a telemarketing agent.

40. The system of claim 34, wherein said agent is a customer service agent.

41. The system of claim 34, wherein the means for causing at least one action to be taken includes means for transmitting at least one signal to the at least one agent.

42. The system of claim 34, wherein the means for causing at least one action to be taken includes means for transmitting at least one signal to at least one reviewing authority.

43. The system of claim 34, wherein the means for causing at least one action to be taken includes means for making an entry in a script compliance incentive system.

44. A method of improving agent performance, the method comprising at least the following:

identifying at least one interaction handled by at least one agent, which interaction is deficient in at least one aspect, the at least one interaction being recorded as a video recording;

obtaining a voice record of at least a portion of the at least one interaction;

obtaining a further voice record of at least a portion of at least a further pre-recorded interaction or a plurality of pre-recorded interactions, wherein the plurality of pre-recorded interactions are stored in a library or data store containing exemplary interactions by the at least one agent made available for future reference, in which the at least one aspect is determined by generating a score using confidence level thresholds of an at least one automatic speech recognition component such that the confidence level thresholds are assigned to each of the plurality of panels and evaluating the score against a static or a varying standard of the least one automatic speech recognition component; and

transmitting data representing at least the portions of the voice record and the further pre-recorded voice record or plurality of pre-recorded interactions to the at least one agent.

45. The method of claim 44, further comprising identifying at least one quality assurance related parameter applicable to at least one interaction involving the at least one agent.

46. The method of claim 45, wherein identifying at least one interaction includes analyzing the at least one interaction against the at least one quality assurance related parameter.

47. The method of claim 44, wherein identifying at least one interaction includes identifying at least one interaction wherein the at least one agent does not comply with at least part of a pre-defined script governing the at least one interaction.

48. The method of claim 44, wherein identifying the at least one interaction includes identifying at least one interaction wherein the at least one agent fails to correctly enter data provided by a third party into a computer-based system.

49. The method of claim 44, wherein identifying at least one interaction includes identifying at least one interaction wherein the at least one agent provides an incorrect response to a question from a third party.

50. The method of claim 44, wherein obtaining a voice record includes recording at least a portion of at least one interaction processed by at least one agent physically located at a call center.

51. The method of claim 44, wherein obtaining a voice record includes recording at least a portion of at least one interaction processed by at least one agent physically located remotely from a call center.

52. The method of claim 44, wherein obtaining a further voice record includes obtaining at least a portion of a pre-recorded interaction.

53. The method of claim 44, wherein obtaining a further voice record includes accessing at least one data store containing data representing at least respective portions of a plurality of pre-recorded interactions.

54. The method of claim 44, wherein obtaining a further voice record includes recording at least a portion of a further interaction occurring subsequently to the at least one interaction.

55. The method of claim 44, wherein transmitting the voice record and the further voice record includes emailing the data representing the voice record and the further voice record to the at least one agent.

56. The method of claim 44, further comprising transmitting to the at least one agent at least one screen shot representation of a computer screen related to the at least one interaction.

57. The method of claim 44, further comprising transmitting to the at least one agent data representing at least a portion of a pre-defined script with which the at least one agent failed to comply.

58. The method of claim 44, further comprising transmitting to the at least one agent data representing information entered incorrectly by the at least one agent into a computer-based system.

59. The method of claim 44, further comprising directing the at least one agent to remedial materials based on the at least one aspect.

60. The method of claim 44, further comprising directing the at least one agent to at least a portion of a software-based training program based on the at least one aspect.

61. The method of claim 44, further comprising directing the agent to at least a portion of a training document based on the at least one aspect.

62. The method of claim 44, further comprising converting the voice record into a format suitable for transmission to at least one agent physically located in a call center.

63. The method of claim 44, further comprising converting the voice record into a format suitable for transmission to at least one agent physically located remotely from a call center.

64. The method of claim 44, further comprising converting the further voice record into a format suitable for transmission to at least one agent physically located in a call center.

65. The method of claim 44, further comprising converting the further voice record into a format suitable for transmission to at least one agent physically located remotely from a call center.

66. The method of claim 44, further comprising converting at least one of the voice record and the further voice record into a format suitable for e-mail transmission.

67. The method of claim 44, further comprising accessing a data store adapted to correlate respective portions of a pre-defined script governing at least a portion of the at least one interaction to respective fields in the data store that store respective suggested voice records corresponding to the respective portions of the script.

68. A computer readable medium storing computer executable instructions, which when executed by a computer, enable the computer to perform a method comprising:

identify at least one interaction handled by at least one agent, which interaction is deficient in at least one aspect, the at least one interaction being recorded as a video recording;

obtain a voice record of at least a portion of the at least one interaction;

obtain a further pre-recorded voice record of at least a portion of at least a further interaction or a plurality of further pre-recorded voice records of at least portions of at least further interactions, wherein the plurality of pre-recorded voice records of at least portions of at least further interactions are stored in a library or data store containing exemplary interactions by the at least one agent made available for future reference, in which the at least one aspect is determined by generating a score using confidence level thresholds of an at least one automatic speech recognition component such that the confidence level thresholds are assigned to each of the plurality of panels and evaluating the score against a static or a varying standard of the least one automatic speech recognition component; and

transmit data representing at least the portions of the voice record and the further pre-recorded voice record to the at least one agent.

69. A system for improving agent performance, the system comprising at least the following:

means for identifying at least one interaction handled by at least one agent, which interaction is deficient in at least one aspect, the at least one interaction being recorded as a video recording;

means for obtaining a voice record of at least a portion of the at least one interaction;

means for obtaining a further pre-recorded voice record of at least a portion of at least a further portion or a plurality of at least portions of at least further pre-recorded voice records, wherein the plurality of at least portions of pre-recorded voice records are stored in a library or data store containing exemplary interactions by the at least one agent made available for future reference, in which the at least one aspect is determined by generating a score using confidence level thresholds of an at least one automatic speech recognition component such that the confidence level thresholds are assigned to each of the plurality of panels and evaluating the score against a static or a varying standard of the least one automatic speech recognition component; and

means for transmitting data representing at least the portions of the voice record and the further pre-recorded voice record or the plurality of pre-recorded voice records to the at least one agent.