Closed Domain Intelligent Human-Machine Dialogue System

Abstract

The present invention proposes a closed-domain intelligent human-computer dialogue system, which includes: a first modeling module, which is used to construct a multi-feature fusion deep intent recognition model based on a bidirectional long-short-term memory network and a convolutional neural network ; The second modeling module is used to construct the dialogue state tracking model based on MC-BLSTM-MSCNN by adopting the joint modeling mode of the current state input of the man-machine dialogue state system and the context sentence; the third modeling module is used to construct the dialogue state tracking model based on mobile The Bi-LSTM matching model of the out-of-domain recovery mechanism of the bit attention mechanism is used to input the recognized user intent and user slot value into the shift network for the weight distribution of the attention mechanism, and realize the encoding of the dialogue state and the matching of dialogue control. The invention has higher intent recognition accuracy, correctness of dialogue state tracking and stability of dialogue control, and further improves the cognitive intelligence ability of the man-machine system.

Description

technical field [0001] The invention relates to the technical field of man-machine dialogue, in particular to an intelligent man-machine dialogue system in a closed domain. Background technique [0002] At present, most of the human-computer dialogue systems in the industry use the method of manually sorting out business logic and writing them into rules for dialogue matching, which do not have higher cognitive intelligence. However, the academic circles mostly focus on a certain implementation part of the human-computer dialogue system, such as dialogue status. Tracking, natural language understanding, etc., do not have a complete solution that fully considers business scenarios, and existing technologies cannot easily solve the low fluency and single-domain problems of human-machine dialogue systems. However, there are three difficulties in the dialogue system of human-computer interaction as follows. [0003] (1) Short text and lack of grammar challenge the accuracy of i...

AI Technical Summary

Problems solved by technology

[0005] (2) The complexity of repeated rounds of human-computer dialogue challenges the intelligence and migration of the dialogue model

[0007] (3) Challenges brought about by all AI-based aspects of the man-machine dialogue system

[0010] However, the intention recognition in the existing dialogue system ignores the short text and lack of grammar in the human-computer dialogue scene, resulting in low recognition accuracy; the dialogue state tracking has not been well applied, resulting in the neglect of the semantic information of the context; dialogue control Ignore the control and recovery of the dialog jumping to a non-domain, and do not implement different feedback for the context, and cannot respond to the dynamic changes of the dialog

Images