METHOD AND APPARATUS FOR EXECUTING A HUMAN-MACHINE DIALOGUE IN THE FORM OF TWO-SIDED SPEECH AS BASED ON A MODULAR DIALOGUE STRUCTURE

摘要

For in a transaction environment executing a machine-controlled human-machine dialogue, the following steps are executed: receiving an access call; in a dialogue structure by means of outputted speech items interrogating the access call whilst examining subsequently received human speech items for ascertaining an actual transaction instance, and outputting speech in accordance with the ascertaining until either attaining a positive transaction result, or otherwise exiting the dialogue in case of failure. In particular, the dialogue is constructed from hierarchically arranged and callable subdialogues which constitute respective mutually independent building blocks, which are arranged for generating a particular outcome if a positive result is attained by the subdialogue in question, and in that they offer interfaces for mutual coupling with a hierarchically superior subdialogue, so that the overall structure is formed as based on a selection of subdialogues and exclusively based on required partial results by each of the subdialogues in the structure.