Conversational Software Agent

A computer-implemented method of effecting communication between a user and an artificial intelligence software agent executed on a computer, the method comprising:

• receiving at an ASR system voice input from the user;
• identifying by the ASR system individual words in the voice input, wherein the ASR system generates in memory a set of one or more words it has identified in the voice input, and updates the set each time it identifies a new word in the voice input to add the new word to the set;
• detecting by the software agent a condition indicative of speech inactivity in the voice input;
• generating by the software agent based on the set of identified words, in response to the detected speech inactivity condition, a response for outputting to the user;
• determining whether the ASR system has identified any more words in the voice input during an interval of time commencing with the detection of the speech inactivity condition;
• and
• outputting the response to the user, by the software agent, after said interval of time has ended and only if the ASR system has not identified any more words in the voice input in that interval of time, whereby the generated response is not outputted to the user if one or more words are identified in the voice input in that interval of time.

A computer program product comprising an artificial intelligence software agent stored on a computer readable storage medium, the software agent for communicating with a user based on the output of an ASR system, the ASR system for receiving voice input from the user and identifying individual words in the voice input, the software agent being configured when executed to perform operations of:

• detecting a condition indicative of speech inactivity in the voice input;
• generating based on the set of identified words, in response to the detected speech inactivity condition, a response for outputting to the user;
• determining whether the ASR system has identified any more words in the voice input during an interval of time commencing with the detection of the speech inactivity condition;
• and
• outputting the response to the user after said interval of time has ended and only if the ASR system has not identified any more words in the voice input in that interval of time, whereby the generated response is not outputted to the user if one or more words are identified in the voice input in that interval of time.