Spoken language understanding and rewriting method based on commercial dialogue system

Abstract

A spoken language understanding and rewriting method based on a commercial dialogue system comprises the following steps: identifying and acquiring domain information related to an utterance accordingto the utterance input by a user; according to the field related to the utterance, identifying and acquiring intention information contained in the utterance; detecting slot position information contained in the user utterance according to the intention information, and storing the detected slot position information; rewritting the utterance input by the user according to the domain information,the intention information and the stored slot position information, and complementing the utterance information; selecting the sub-dialogue system to provide service according to the domain information and intention information of the utterance input by the user. According to the method, the problem of semantic transmission blockage easily appearing in a commercial dialogue system can be solved. Through the application of the method, when the sub-dialogue system is switched due to the change of the user demand, the sub-dialogue system can know the user demand according to the rewritten user utterance and is not perceived by the user, so that the use experience of the user can be ensured to the maximum extent.

Description

technical field [0001] The invention relates to the technical field of language processing, in particular to a method for understanding and rewriting spoken language based on a commercial dialogue system. Background technique [0002] Usually in a multi-turn task completion dialogue system, there is a dedicated dialogue state tracker to track the state of the dialogue. However, in the commercial field, a complete dialogue system often consists of multiple sub-dialogue systems that are responsible for different functions. , and these sub-dialogue systems may not all be task-completion dialog systems, so there is no dedicated dialog state tracker. For example, a dialog system consists of a weather query dialog system and an airline ticket order dialog system. The former is a dialog based on a single round of queries. system, does not contain a dialogue state tracker, while the latter is a dialogue system based on multiple rounds of queries, and contains a dialogue state tracke...

AI Technical Summary

Problems solved by technology

[0002] Usually in a multi-turn task completion dialogue system, there is a dedicated dialogue state tracker to track the state of the dialogue. However, in the commercial field, a complete dialogue system often consists of multiple sub-dialogue systems that are responsible for different functions. , and these sub-dialogue systems may not all be task-completion dialog systems, so there is no dedicated dialog state tracker. For example, a dialog system consists of a weather query dialog system and an airline ticket order dialog system. The former is a dialog based on a single round of queries. system, does not contain a dialogue state tracker, while the latter is a dialogue system based on multiple rounds of queries, and contains a dialogue state tracker, when the user's needs switch between these two systems, historical dialogue information cannot be called by another system, When a user inquires about air tickets to a certain place, the air ticket order dialogue system provides services for the user. When the user then asks what the weather is like there, the weather inquiry dialogue system has no way to obtain the specific location based on "what is the weather there?" information, and the location is stored in the dialog status tracker of the ticket ordering dialog system, and the weather query dialog system cannot obtain it, so it cannot answer. This kind of semantic transfer blocking problem will lead to unsmooth man-machine dialogue and affect users. Experience

Images