Semantic decision-making method and system based on white list and medium

Abstract

The invention provides a semantic decision-making method and system based on a white list and a medium, and relates to the technical field of man-machine conversation, and the method comprises the steps of: S1, constructing a non-basic domain semantic understanding micro-service and a basic domain semantic understanding micro-service according to a business demand; S2, constructing a white list according to business logic; S3, simultaneously inputting a text into the non-basic domain semantic understanding micro-service and the basic domain semantic understanding micro-service to obtain a corresponding result; and S4, judging whether the non-basic domain skills are in the white list or not and whether the confidence coefficient of the non-basic domain skills is greater than a set value or not according to the result, and acquiring a final semantic result. According to the method, the final semantic result can be decided by adopting the white list, so that the semantic understanding accuracy and performance are improved, and meanwhile, the user experience of man-machine conversation is ensured.

Description

technical field [0001] The present invention relates to the technical field of man-machine dialogue, in particular to a whitelist-based semantic decision-making method, system and medium. 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. Semantic understanding is a very important part of human-machine dialogue. Especially in vehicle-mounted voice interaction systems, the semantic understanding models of some domain skills require more than one million user corpora to train and learn. Insufficiently, the semantic understanding service of the external basic domain may be used first. At this time, the problem of making a decision between the semantic understa...

AI Technical Summary

Problems solved by technology

[0004] The existing technology compares the confidence of basic domain semantic understanding with that of non-basic domain semantic understanding, and the larger one is regarded as the best semantic result. This may not necessarily select a better semantic result. Business skills in different domains can be compared Sex is not strong

Images