Abstract: An interactive dialogue apparatus generates prompts and receives responses which it processes and stores response data. Progress of the dialogue is controlled using a state model which is parsed, comparing transition conditions with the stored response data, stopping at a state for which no edge condition is satisfied. Each time a fresh response is received, the model is reparsed from the start. Prompts are generated by reference to a state history, being selected by finding the longest match between the history and state sequences associated with stored prompts. Prompts are compared so that the dialogue may be terminated in the event of repetition.

Abstract: In this invention dialogue states for a dialogue model are created using a training corpus of example human—human dialogues. Dialogue states are modelled at the turn level rather than at the move level, and the dialogue states are derived from the training corpus. The range of operator dialogue utterances is actually quite small in many services and therefore may be categorized into a set of predetermined meanings. This is an important assumption which is not true of general conversation, but is often true of conversations between telephone operators and people. Phrases are specified which have specific substitution and deletion penalties, for example the two phrases “I would like to” and “can I” may be specified as a possible substitution with low or zero penalty. Thus allows common equivalent phrases are given low substitution penalties. Insignificant phrases such as ‘erm’ are given low or zero deletion penalties.

Abstract: An interactive dialogue apparatus generates prompts and receives responses which it processes and stores response data. Progress of the dialogue is controlled using a state model which is parsed, comparing transition conditions with the stored response data, stopping at a state for which no edge condition is satisfied. Each time a fresh response is received, the model is reparsed from the start. Prompts are generated by reference to a state history, being selected by finding the longest match between the history and state sequences associated with stored prompts. Prompts are compared so that the dialogue may be terminated in the event of repetition.

Abstract: In this invention dialogue states for a dialogue model are created using a training corpus of example human-human dialogues. Dialogue states are modelled at the turn level rather than at the move level, and the dialogue states are derived from the training corpus.