Method and apparatus for recording/replaying application execution with recorded voice recognition utterances

摘要

A diagnostic tool for speech recognition applications is provided, which enables a administrator to collect multiple recorded speech sessions. The administrator can then search for various failure points common to one or more of the recorded sessions in order to get a list of all sessions that have the same failure points. The invention allows the administrator to playback the session or replay any portion of the session to see the flow of the application and the recorded utterances. The invention provides the administrator with information about how to maximize the efficiency of the application which enables the administrator to edit the application to avoid future failure points.

主权项

1. A method of increasing an efficiency of a speech recognition application comprising:
receiving, by a speech recognition application, a call identification (CallID) associated with a respective one of a plurality of sessions; recording, on a storage device: said session of the plurality of sessions, and the CallID of said session; shutting off a recording of said session during time when confidential information is expected to be received; detecting, by the speech recognition application, an event, wherein the event comprises a communication failure of one session of said plurality of sessions; determining, by the speech recognition application, that a quantity of detected events that share a common attribute exceeds a predetermined threshold; grouping said recorded sessions determined to have said common attribute; and providing access to at least two of said grouped recorded sessions for review.