Rejection method and device, equipment and storage medium

Abstract

The invention provides an identification rejection method and device, equipment and a storage medium. The method comprises the following steps: acquiring to-be-identified target information; inputting the target information into a pre-trained function recognition model to obtain a target business function corresponding to the target information; inputting the target information into a pre-trained intention classification model to obtain a target intention type corresponding to the target information; and determining whether to reject the target information according to the target business function and the target intention type. According to the rejection method provided by the invention, whether the target intention type corresponding to the target information accords with the intention type supported by the corresponding target service function is judged to distinguish whether the target information is the functional range verbal skill or the non-functional range verbal skill for the target service type, and rejection is performed on the non-functional range verbal skill, so that the rejection rate of the target information is improved. The information rejection accuracy of the voice interaction system is improved, the rejection task in the voice interaction system is optimized, and the rejection effect is improved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a recognition rejection method, device, equipment and storage medium. Background technique [0002] With the advancement of artificial intelligence technology, human-computer voice interaction has also made great progress. In order to improve the user experience, the full-duplex voice interaction mode has gradually appeared. The feature of the full-duplex voice interaction mode is that after one wake-up, After a certain period of time, multiple consecutive interactions can be performed. [0003] In the full-duplex voice interaction mode, the intelligent voice system needs to continuously record the voice input by the user, and perform natural language understanding and reply to the recorded voice. In this mode, it is necessary to accurately identify some voices input by the user that are not interacting with the system (such as chatting with other people,...

AI Technical Summary

Problems solved by technology

This type of classification model is mainly based on the content of the speech. For example, it can distinguish whether the user's sentence is to listen to a song, or ask about the weather, or a sentence that has nothing to do with the content involved in the function. However, for similar information content, different intentions When using discourse data (such as "I'm going to Shanghai" and "I've been to Shanghai"), the discrimination effect is often not very good, resulting in poor recognition rejection and affecting user experience

Images