The method of building expectation model in task-oriented dialogue systems and its realization algorithms

In human-machine interaction, an effective way to improve the accuracy of semantic analysis is to deduce the users´ intentions by setting expectations. We mainly illustrate how to extract common structures and processing methods of the expectation model (EM) from a scene-specified expectation setting. We then propose algorithms for building and applying EM in spoken dialogue systems. By analyzing the characteristics of system task structure, our algorithms can be used to generate appropriate expectations. After incorporation into the dialogue context, the EM can help create a more reasonable dialogue situation, which endows the system with the preliminary ability to deduce users´ intentions by reference to this situation, so as to improve the robustness of semantic analysis and the transaction-success rate.