This paper aims to describe diverse request patterns in Chinese for the automatic classification and the Chinese-Korean translation of music-request sentences in AI assistant platforms. These patterns are formalized by Local-Grammar Graphs (LGGs), i.e. finite-state grammars represented in the form of directed acyclic graphs based on the main function categories. The Chinese LGGs were constructed with the aid of the UNITEX graph editor, and the request pattern tags proposed for Korean sentences in the DECO Korean Electronic dictionaries were applied. The result of this study was examined and evaluated by comparison with Google Translate results. Experimental results prove that the LGG grammar constructed in this paper can effectively cover and annotate various request patterns. This will provide the possibility to generate a large-scale bilingual annotation corpus in the field of music listening.