Shale oil occurs in varying forms within porous media, with diverse micro-occurrences exhibiting intricate topological characteristics within the pores. The impact of shale oil presence on fluid flow patterns in these complex environments remains uncertain. This study investigates how different shale oil micro-occurrence types and saturation levels influence pore network characteristics and fluid flow behavior in shale reservoirs. Firstly, the shale digital core is established using the focused ion beam scanning electron microscope (FIB-SEM) method, and the pore skeleton is segmented via the watershed method. Utilizing the quartet structure generation set method, we constructed 12 digital cores representing floating, cementing, and coating shale oil micro-occurrence types at different oil saturations based on the real digital core model. The pore network analysis, conducted using the maximum ball method, revealed that increasing oil saturation generally leads to a reduction in pore radius and an increase in pore quantity due to pore subdivision, with the cementing type showing the most significant effect. Additionally, machine learning techniques, including random forest, support vector machine (SVM), and K-nearest neighbors (KNN), were employed to classify micro-occurrence types of shale oil based on topological features such as volume ratio, cross-sectional area ratio, three-dimensional shape factor, and Euler number. The support vector machine (SVM) method achieved the highest predictive accuracy (93%), outperforming the random forest (91%) and KNN (75%) methods, indicating its effectiveness in discerning subtle differences between micro-occurrence types. Lattice Boltzmann simulations were employed to study the impact of shale oil micro-occurrence type and saturation on fluid flow properties within the pore networks. Results showed that coating shale oil exhibited the highest permeability, followed by floating, whereas cementing shale oil caused a notable reduction in permeability due to pore blockage. This study enhances the understanding of the intricate relationship between shale oil geometric micro-occurrence patterns, pore structure, and fluid flow behavior within a digital-core framework, providing valuable insights into pore-scale fluid dynamics in shale reservoirs.