Apparatus and method for processing service interactions
View Patent ↗An interactive voice and data response system that directs input to a voice, text, and web-capable software-based router, which is able to intelligently respond to the input by drawing on a combination of human agents, advanced speech recognition and expert systems, connected to the router via a TCP/IP network. The digitized input is broken down into components so that the customer interaction is managed as a series of small tasks performed by a pool of human agents, rather than one ongoing conversation between the customer and a single agent. The router manages the interactions and keeps pace with a real-time conversation. The system utilizes both speech recognition and human intelligence for purposes of interpreting customer utterances or customer text, where the role of the human agent(s) is to input the intent of caller utterances, and where the computer system—not the human agent—determines which response to provide given the customer's stated intent (as interpreted/captured by the human agents). The system may use more than one human agent, or both human agents and speech recognition software, to interpret simultaneously the same component for error-checking and interpretation accuracy.
1. A computer-implemented method for operating an interactive response system comprising:
receiving data representing a multi-utterance transaction with a person, the data having multiple elements, a subset of the elements including sensitive customer data;
portioning the multi-utterance transaction into discrete, logical utterance units;
automatically presenting the utterance units in perceptible form through a routing device and an analyst interface to each of a number of intent analysts, the utterance units being distributed so that no intent analyst is ever exposed to more than one of said subset of the elements including sensitive customer data;
accepting intent input from each intent analyst through the respective analyst user interface, where the intent input characterizes the intent analyst's interpretation of the person's intent expressed in the utterance unit; and
using a processor, automatically communicating a message to the person, in perceptible form and in substantially real time relative to the receiving step, the message being automatically selected from among a predetermined set of possible messages as a function of the intent input accepted from the intent analysts.
2. The method of claim 1 , wherein the multi-utterance transaction comprises audio.
3. The method of claim 2 , wherein the multi-utterance transaction is received through a telephone system.
4. The method of claim 1 , wherein the multi-utterance transaction comprises video.
5. The method of claim 1 , wherein the number of intent analysts is at least two.
6. The method of claim 5 , wherein the presenting occurs to all of the at least two intent analysts at substantially the same time.
7. The method of claim 1 , further comprising accepting data input from each intent analyst through the respective analyst user interface, where the data input characterizes data expressed by the person in one of the utterance units.
8. The method of claim 1 , further comprising automatically changing the number of intent analysts to whom one of the utterance units is presented depending on a load factor, the utterance units still being distributed so that no intent analyst is ever exposed to more than one of said subset of the elements including sensitive customer data.
9. The method of claim 8 , wherein the number is initially at least three, but is automatically decreased to a new number when the load factor becomes higher than a predetermined threshold, where the new number is at least two.
10. The method of claim 9 , wherein the number is automatically increased when the load factor becomes lower than a predetermined threshold.
11. The method of claim 1 wherein, in connection with the presenting step, contextual information about the person's interactive session with the system is displayed to each of the intent analysts through the respective analyst user interface.
12. The method of claim 1 , wherein the presentation to the intent analysts occurs in at least two geographically diverse locations.
13. The method of claim 1 , wherein the perceptible form of the utterance units is accelerated relative to the speed as made by the person.
14. The method of claim 1 , further comprising: evaluating the accuracy, in real time, of the intent input from each of the intent analysts, and updating a profile for the respective intent analyst.
15. The method of claim 1 , further comprising objectively rating the speed and accuracy of the intent input from at least one of the intent analysts.
16. The method of claim 1 , further comprising rating the speed and accuracy of the intent input from at least one of the intent analysts relative to at least one other one of the intent analysts.
17. The method of claim 1 , wherein the presenting step comprises selecting the number of intent analysts from a larger pool of intent analysts as a function of whether each intent analyst has already been exposed to confidential or personally identifiable information for the person.
18. A system for processing an interaction with a person, comprising a processor, two or more analyst user interface devices in communication with the processor, and a memory in communication with the processor, the memory storing programming instructions executable by the processor to:
receive data representing a multi-utterance transaction with the person, the data having multiple elements, a subset of the elements including sensitive customer data;
portion the multi-utterance transaction into discrete, logical utterance units;
automatically present the utterance units in perceptible form through the analyst interface devices to a number of intent analysts, the utterance units being distributed so that no intent analyst is ever exposed to more than one of said subset of the elements including sensitive customer data;
accept intent input from each intent analyst through the respective analyst user interface device, where the intent input characterizes the intent analyst's interpretation of the person's intent expressed in the utterance, and where the intent input is prevented from providing information to be communicated to the person; and
automatically communicate a message to the person, in perceptible form and in substantially real time relative to the receiving function, the message being automatically selected from among a predetermined set of possible messages as a function of the intent input accepted from the two or more intent analysts.
19. The system of claim 18 , wherein the multi-utterance transaction comprises audio.
20. The system of claim 19 , wherein the multi-utterance transaction is received from the person through a telephone system.
21. The system of claim 18 , wherein the multi-utterance transaction comprises video.
22. The system of claim 18 , wherein the programming instructions are further executable by the processor to accept data input from each intent analyst through the respective analyst user interface device, and where the data input characterizes the intent analysts transcription of data expressed by the person in one of the utterance units.
23. The system of claim 18 , wherein the programming instructions are further executable by the processor to automatically change the number of intent analysts to whom one of the utterance units is presented depending on a load factor, the utterance units still being distributed so that no intent analyst is ever exposed to more than one of said subset of the elements including sensitive customer data.
24. The system of claim 18 , wherein the number is initially at least three, but is automatically decreased to a new number when the load factor becomes higher than a predetermined threshold, where the new number is at least two.
25. The system of claim 18 , wherein the number is automatically increased when the load factor becomes lower than a predetermined threshold.
26. The system of claim 18 , wherein the programming instructions are further executable by the processor, in connection with the presenting step, to display contextual information about the person's interactive session with the system to each of the two or more intent analysts through the respective analyst user interface device.
27. The system of claim 18 , wherein the analyst user interface devices are geographically diverse.
28. The system of claim 18 , wherein the programming instructions are further executable by the processor, in connection with the presenting step, so that the perceptible form of the utterance units is accelerated relative to the speed as made by the person.
29. The system of claim 18 , wherein the programming instructions are further executable by the processor to: evaluate the accuracy, in real time, of the intent input from each of the intent analysts, and update a profile for the respective intent analyst.
30. The system of claim 18 , wherein the programming instructions are further executable by the processor to objectively rate the speed and accuracy of the intent input from at least one of the intent analysts.
31. The system of claim 18 , wherein the programming instructions are further executable by the processor to rate the speed and accuracy of the intent input from at least one of the intent analysts relative to at least one other one of the intent analysts.
32. The system of claim 18 , wherein the automatic presenting comprises selecting the number of intent analysts from a larger pool of intent analysts as a function of whether each intent analyst has already been exposed to confidential or personally identifiable information for the person.
33. A system for managing interactions with a person, comprising a processor and a memory in communication with the processor, the memory storing programming instructions executable by the processor to:
receive data representing a multi-utterance transaction with the person, the data having multiple elements, a subset of the elements including sensitive customer data;
portion the multi-utterance transaction into discrete, logical utterance units;
automatically send the utterance units to two or more intent analyst user interface devices, each user interface device being configured to reproduce the utterance in a form perceptible to an intent analyst, the utterance units being distributed so that no intent analyst is ever exposed to more than one of said subset of the elements including sensitive customer data;
receive intent input from each intent analyst user interface device, where the intent input characterizes an intent analyst's interpretation of the person's intent expressed in the utterance,
automatically communicate a message to the person in perceptible form and in substantially real time relative to the receiving function, the message being automatically selected from among a predetermined set of possible messages as a function of the intent input received from the two or more intent analyst user interface devices.
34. The system of claim 33 , wherein the multi-utterance transaction comprises audio.
35. The system of claim 34 , wherein the multi-utterance transaction is received from the person through a telephone system.
36. The system of claim 33 , wherein the multi-utterance transaction comprises video.
37. The system of claim 33 , wherein the programming instructions are further executable by the processor to accept data input from each intent analyst through the respective analyst user interface device, and where the data input characterizes data expressed by the person in one of the utterance units.
38. The system of claim 33 , wherein the programming instructions are further executable by the processor to automatically change a number of intent analysts to whom one of the utterance units is presented depending on a load factor, the utterance units still distributed so that no intent analyst is ever exposed to more than one of said subset of the elements including sensitive customer data.
39. The system of claim 38 , wherein the number is initially at least three, but is automatically decreased to a new number when the load factor becomes higher than a predetermined threshold, where the new number is at least two.
40. The system of claim 38 , wherein the number is automatically increased when the load factor becomes lower than a predetermined threshold.
41. The system of claim 33 , wherein the programming instructions are further executable by the processor, in connection with the presenting step, to display contextual information about the person's interactive session with the system to each of the two or more intent analysts through the respective analyst user interface device.
42. The system of claim 33 , wherein the analyst user interface devices are geographically diverse.
43. The system of claim 33 , wherein the programming instructions are further executable by the processor, in connection with the presenting step, to accelerate one of the utterance units relative to the speed at which it was made.
44. The system of claim 33 , wherein the programming instructions are further executable by the processor to: evaluate the accuracy, in real time, of the intent input from each of the intent analysts, and update a profile for the respective intent analyst.
45. The system of claim 33 , wherein the programming instructions are further executable by the processor to objectively rate the speed and accuracy of the intent input from at least one of the intent analysts.
46. The system of claim 33 , wherein the automatic presenting comprises selecting the two or more intent analysts from a larger pool of intent analysts as a function of whether each intent analyst has already been exposed to confidential or personally identifiable information for the person.