Method and apparatus of estimating optimum dialog state timeout settings in a spoken dialog system

摘要

Example embodiments of the present invention may include a method that includes collecting caller response timings to each of a plurality of dialog states conducted during a call, and estimating a plurality of parameters based on the caller response timings. The method may also include selecting a response completeness value responsive to the estimated plurality of parameters, the response completeness value is used to calculate at least one optimal timeout value. The method may also include selecting the at least one optimal timeout value, and setting the at least one optimal timeout value for each of the corresponding dialog states. The timeout value(s) may be used for subsequent calls to provide optimal user satisfaction and call success rates.

主权项

1. A method, comprising:
collecting caller responses to each of a plurality of dialog states conducted during a call; associating timestamps with each of the caller responses received; identifying caller response timings corresponding to the caller responses and storing the caller response timings and the timestamps in memory at a call processing server, wherein the caller response timings are a function of times when the plurality of dialog states are presented to the caller during the call and times when the caller responses to the plurality of dialog states were received and associated with the timestamps; selecting a response completeness value as a percentage of the total callers that have provided caller responses; calculating at least one optimal timeout value associated with the call based on the selected response completeness value; selecting the at least one optimal timeout value; and setting the at least one optimal timeout value based on a majority of the caller responses at the call processing server for each of the corresponding plurality of dialog states to timeout during at least one of the call and a subsequent call.