The microstructure of metallic materials, particularly their strain characteristics, constitutes the core determinant of macroscopic physicochemical properties; therefore, achieving rapid, precise, and in-situ characterization of microstructure is important for research on metallic materials. Since the microstructure of materials can modulate plasma excitation conditions, microstrain information in metallic materials can be reflected through plasma emission spectra. Laser-induced breakdown spectroscopy (LIBS) has been conventionally employed for detecting elemental composition and conducting quantitative analysis of elemental content; however, investigations of microstrain based on LIBS remain unreported. In this study, we, for the first time, utilized spectroscopic information from laser-induced plasma to establish a classification model for microstrain. Furthermore, by integrating artificial intelligence algorithms, we constructed a quantitative relationship model between spectral characteristics and microstrain, thereby realizing online in-situ quantitative analysis of microstrain. We also conducted an in-depth investigation into the influence mechanism of microstructure on plasma spectra, providing a solid theoretical and experimental foundation for rapid diagnosis of material microstrain based on LIBS technology.