Semantic comprehension processing method and device, equipment and readable storage medium

Abstract

The embodiment of the invention provides a semantic comprehension processing method and device, equipment and a readable storage medium, and the method comprises the steps: carrying out the word segmentation of a to-be-analyzed statement, and setting corresponding labels for a word segmentation result, wherein the labels comprise part-of-speech labels used for representing universal part-of-speechand dictionary labels used for representing special part-of-speech; substituting the label into the to-be-analyzed statement to obtain an updated to-be-analyzed statement, and matching the updated to-be-analyzed statement with a preset matching rule to obtain a matching result, wherein the matching rule comprises an intention and a rule, and the rule at least comprises an N-tuple formed by connecting segmented words through separator marks; representing keywords in the rules by the dictionary labels corresponding to the keywords, and representing non-keywords in the rules by the non-keywordsthemselves. The rule in the embodiment of the invention supports multiple matching modes, and can meet the generalization requirement of the semantic comprehension rule.

Description

technical field [0001] The present invention relates to the field of semantic understanding, in particular to a semantic understanding processing method, device, equipment and readable storage medium. Background technique [0002] Communicating with and understanding others using natural language is one of the hallmarks of human intelligence and one of the most challenging abilities for artificial intelligence. How to make machines understand the semantics contained in natural language is an important task in the development of artificial intelligence technology. [0003] Existing methods for realizing semantic understanding are mainly based on neural models. Neural network-based solutions often require a large amount of training data to improve the effect. At the same time, when there is a problem with the effect of the model, the model needs to be retrained. The semantic understanding effect of a certain sentence pattern is not good, and the needs of users are different i...

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a semantic understanding processing method, device, device, and readable storage medium to solve the problems in the prior art that the semantic understanding method is not strong in generalization ability and the labor cost of constructing rules is high

Images