System and method for optimizing prompts for speech-enabled applications
View Patent ↗A computer-implemented method is described for optimizing prompts for a speech-enabled application. The speech-enabled application is operable to receive communications from a number of users and communicate one or more prompts to each user to illicit a response from the user that indicates the purpose of the user's communication. The method includes determining a number of prompt alternatives (each including one or more prompts) to evaluate and determining an evaluation period for each prompt alternative. The method also includes automatically presenting each prompt alternative to users during the associated evaluation period and automatically recording the results of user responses to each prompt alternative. Furthermore, the method includes automatically analyzing the recorded results for each prompt alternative based on one or more performance criteria and automatically implementing one of the prompt alternatives based on the analysis of the recorded results.
1. A computer-implemented method for optimizing prompts for a speech-enabled application, the speech-enabled application operable to receive a communication from each of a plurality of users and to communicate one or more prompts to each user to illicit one or more responses from the user indicating the purpose of the user's communication, the method comprising:
determining a plurality of prompt alternatives to evaluate, each prompt alternative comprising one or more prompts;
determining an evaluation period for each prompt alternative;
automatically presenting each prompt alternative to one or more users during the associated evaluation period;
automatically recording one or more results of one or more responses to each prompt alternative received from the users;
automatically analyzing the recorded results for each prompt alternative based on one or more performance criteria; and
automatically implementing one of the prompt alternatives based on the analysis of the recorded results.
2. The method of claim 1 , wherein:
one or more of the prompt alternatives comprise a combination of prompts; and
the method further comprises determining the order in which to present the prompts in the combination.
3. The method of claim 1 , wherein the evaluation period comprises the period during which a selected number of user communications are received at the speech-enabled application.
4. The method of claim 1 , wherein the evaluation period comprises a selected length of time.
5. The method of claim 1 , wherein recording one or more results of one or more responses comprises recording the number of direct routes that result from the user responses to each prompt alternative.
6. The method of claim 5 , wherein analyzing the recorded results for each prompt alternative comprises determining which prompt alternative has the highest percentage of direct routes.
7. The method of claim 1 , wherein:
the speech-enabled application is operable to match one or more user responses with an action-object based on one or more salient terms in the user responses that are associated with the action-object; and
recording one or more results of one or more responses comprises recording the number of user responses that the speech-enabled application is able to match with an action-object.
8. The method of claim 7 , wherein analyzing the recorded results for each prompt alternative comprises determining which prompt alternative has the highest percentage of responses that the speech-enabled application is able to match with an action-object.
9. The method of claim 1 , wherein the speech-enabled application comprises a call center.
10. The method of claim 1 , wherein the steps of the method are repeating periodically after implementation of the speech-enabled application.
11. A computer-implemented system for optimizing prompts for a speech-enabled application, the speech-enabled application operable to receive a communication from each of a plurality of users and to communicate one or more prompts to each user to illicit one or more responses from the user indicating the purpose of the user's communication, the system comprising:
a test control module operable to:
determine a plurality of prompt alternatives to evaluate, each prompt alternative comprising one or more prompts; and
determine an evaluation period for each prompt alternative;
a dialog module operable to present each prompt alternative to one or more users during the associated evaluation period; and
a test analysis module operable to:
record one or more results of one or more responses to each prompt alternative received from the users;
analyze the recorded results for each prompt alternative based on one or more performance criteria; and
implement one of the prompt alternatives based on the analysis of the recorded results.
12. The system of claim 11 , wherein:
one or more of the prompt alternatives comprise a combination of prompts; and
the test control module is further operable to determine the order in which to present the prompts in the combination.
13. The system of claim 11 , wherein the evaluation period comprises the period during which a selected number of user communications are received at the speech-enabled application.
14. The system of claim 11 , wherein the evaluation period comprises a selected length of time.
15. The system of claim 11 , wherein recording one or more results of one or more responses comprises recording the number of direct routes that result from the user responses to each prompt alternative.
16. The system of claim 15 , wherein analyzing the recorded results for each prompt alternative comprises determining which prompt alternative has the highest percentage of direct routes.
17. The system of claim 11 , wherein:
the speech-enabled application is operable to match one or more user responses with an action-object based on one or more salient terms in the user responses that are associated with the action-object; and
recording one or more results of one or more responses comprises recording the number of user responses that the speech-enabled application is able to match with an action-object.
18. The system of claim 17 , wherein analyzing the recorded results for each prompt alternative comprises determining which prompt alternative has the highest percentage of responses that the speech-enabled application is able to match with an action-object.
19. The system of claim 11 , wherein the speech-enabled application comprises a call center.
20. Software for optimizing prompts for a speech-enabled application, the speech-enabled application operable to receive a communication from each of a plurality of users and to communicate one or more prompts to each user to illicit one or more responses from the user indicating the purpose of the user's communication, the software embodied in a computer-readable medium and when executed operable to:
determine a plurality of prompt alternatives to evaluate, each prompt alternative comprising one or more prompts;
determine an evaluation period for each prompt alternative;
present each prompt alternative to one or more users during the associated evaluation period;
record one or more results of one or more responses to each prompt alternative received from the users;
analyze the recorded results for each prompt alternative based on one or more performance criteria; and
implement one of the prompt alternatives based on the analysis of the recorded results.
21. The software of claim 20 , wherein:
one or more of the prompt alternatives comprise a combination of prompts; and
the software is further operable to determine the order in which to present the prompts in the combination.
22. The software of claim 20 , wherein the evaluation period comprises the period during which a selected number of user communications are received at the speech-enabled application.
23. The software of claim 20 , wherein the evaluation period comprises a selected length of time.
24. The software of claim 20 , wherein recording one or more results of one or more responses comprises recording the number of direct routes that result from the user responses to each prompt alternative.
25. The software of claim 24 , wherein analyzing the recorded results for each prompt alternative comprises determining which prompt alternative has the highest percentage of direct routes.
26. The software of claim 20 , wherein:
the speech-enabled application is operable to match one or more user responses with an action-object based on one or more salient terms in the user responses that are associated with the action-object; and
recording one or more results of one or more responses comprises recording the number of user responses that the speech-enabled application is able to match with an action-object.
27. The software of claim 26 , wherein analyzing the recorded results for each prompt alternative comprises determining which prompt alternative has the highest percentage of responses that the speech-enabled application is able to match with an action-object.
28. The software of claim 20 , wherein the speech-enabled application comprises a call center.