The classical fuzzy system model method kindly assumed data which is generated from single task. This data can be acquired from the perspective of multiple task the modeling has on intrinsic inconsistency. In this project , a multiple fuzzy system modeling method by mining interact common hidden structure is propose to overcome the weakness of classical TSK- based fuzzy modeling method system for multitask learning. When the classical fuzzy modeling method are applied to multitask datasets, they usually focus on the task independence information and the ignore the correlation between different task. Here we mine the common hidden structure among multiple tasks to realize multitask TSK fuzzy system learning it makes good used of the independence information of each task and correlation information captured by common hidden structure among all tasks as well. Thus, the proposed learning algorithm can effectively improve both the generalization and fitting performance of the learned fuzzy system for each task . Our experiment result demonstrate at the proposed MTCS-TSK_FS has better modeling performance and adaptability than the existing TSK based fuzzy modeling method on multitask datasets. Learning multiple tasks across different datasets is a challenging problem since the feature space may not be the same for different tasks. The data can be any type or the datasets. The data can be any type or the datasets are any type like text datasets.