<p>Human interaction recognition through WiFi channel information has emerged as a promising approach for various applications, including surveillance and smart environments. This paper proposes a novel, optimized Gated Recurrent Unit-Based Recurrent Neural Network (GRU-RNN) framework designed specifically for accurate and efficient human interaction recognition using WiFi Channel State Information (CSI). The novelty of this work lies in the development of an advanced optimization strategy for GRU-RNN, which not only enhances recognition accuracy but also significantly reduces computational overhead, making the model practical for real-time applications. To validate its efficacy, the proposed method is compared against state-of-the-art approaches, demonstrating superior performance in recognition accuracy, processing speed, and scalability. Additionally, we introduce a user-friendly graphical user interface (GUI) for real-time interaction and visualization, bridging the gap between research and practical deployment. Experimental evaluations across diverse scenarios highlight the robustness and adaptability of the system, underscoring its potential for deployment in dynamic smart environments and interactive systems.</p>