Rule matching method, device and equipment and storage medium

Abstract

The embodiment of the invention discloses a rule matching method and device, equipment and a storage medium, and the method comprises the steps: determining a user instruction text; performing entitymatching on the user instruction text based on a knowledge graph, and determining a matched target entity; replacing the target entity with a semantic slot corresponding to the target entity to obtaina new user instruction text; and performing rule matching on the new user instruction text to obtain a target rule matched with the new user instruction text, and taking the target rule as a rule matched with the user instruction text. According to the technical scheme provided by the embodiment of the invention, the entity in the user instruction text can be accurately identified, the identification accuracy is improved, multiple language scenes can be covered, and the requirement for identifying multiple types of texts is met.

Description

technical field [0001] Embodiments of the present invention relate to intent recognition technologies, and in particular to a rule matching method, device, equipment and storage medium. Background technique [0002] In recent years, with the rapid development of speech recognition, man-machine dialogue, natural language processing and other technologies. User intent recognition is an extremely important and challenging task for this type of assistant dialogue product. User intent recognition is to understand the user's needs from the user's input. [0003] Among them, the intention recognition method may be based on rules for matching, so as to recognize voice slots, and then recognize user intentions. However, the inventor found the following problems in the prior art during the specific implementation process: the matching rule method in the prior art cannot accurately identify the entities in the user instruction text, which reduces the recognition accuracy. Moreover, ...

AI Technical Summary

Problems solved by technology

However, the inventor found the following problems in the prior art during the specific implementation process: the matching rule method in the prior art cannot accurately identify the entities in the user instruction text, which reduces the accuracy of identification

Moreover, in the rule matching process in the prior art, entities in the user instruction text are matched with the rules. Due to the limited rules, it is difficult to cover many scenarios.

Images