Semantic comprehension and dialogue management fusion method and system based on hash table

Abstract

The invention provides a semantic comprehension and dialogue management fusion method and system based on a hash table. The method comprises the following steps that S1, semantic comprehension micro-services are constructed according to business requirements; s2, constructing a hash table and a plurality of dialogue management micro-services according to business logic; s3, inputting the text into a semantic understanding micro-service to obtain a semantic result; s4, mapping to a corresponding dialogue management micro-service through a hash table according to the skill of the semantic result; and S5, giving a corresponding reply according to the mapped dialogue management micro-service. According to the invention, the skill of the semantic result is mapped to the corresponding dialogue management module by adopting the hash table, so that the dialogue performance is improved, and meanwhile, the good user experience of man-machine dialogue is ensured; the skill of the semantic result is mapped to the corresponding dialogue logic module by adopting the hash table, so that the dialogue performance is improved, and meanwhile, the good user experience of man-machine dialogue is ensured.

Description

technical field [0001] The present invention relates to the technical field of semantic understanding, in particular to a hash table-based semantic understanding and dialogue management fusion method and system. Background technique [0002] Natural language is the crystallization of human wisdom, and it has been a long-standing expectation for people to interact with computers in the form of natural language. With the development of natural language processing technology and the rise of deep learning methods, the human-computer dialogue system has become a new research hotspot. [0003] In the patent document with the publication number CN106528522A, a scene-based semantic understanding and dialogue generation method and system are disclosed. By establishing a user scene model, the field of the current conversation is selected and determined according to the results of the word segmentation system; the selected scene semantic analysis is adopted The machine understands the...

AI Technical Summary

Problems solved by technology

[0004] The fusion of semantic understanding and dialogue management is a very important part of human-computer dialogue. If the fusion method of semantic understanding and dialogue management is not good, it may affect the accuracy and performance of the dialogue, so that a good user experience of human-computer dialogue cannot be guaranteed.

Images