This paper proposes END4Rec, a method for efficient noise-decoupling in multi-behavior sequential recommendation. The main contributions include: (1) Introducing an Efficient Behavior Sequence Miner (EBM) that captures complex user patterns with low computational cost. (2) Designing a Behavior-Aware Denoising module with Hard Noise Eliminator and Soft Noise Filter to effectively remove noise from user behavior data. (3) Introducing Noise-Decoupling Contrastive Learning and a guided training strategy to achieve effective noise removal and enhance the decoupling of noise signals. (4) Conducting comprehensive experiments on three real-world datasets, demonstrating the effectiveness and efficiency of END4Rec in handling multi-behavior sequential recommendation. The method addresses the challenges of efficiently mining user behavior sequences and reducing noise signals in multi-behavior sequential recommendation. The EBM module efficiently captures intricate patterns in user behavior while maintaining low time complexity and parameter count. The Behavior-Aware Denoising module includes Hard Noise Eliminator and Soft Noise Filter to remove different types of noise. The Noise-Decoupling Contrastive Learning and guided training strategy are used to contrast valid information with noisy signals and seamlessly integrate the two denoising processes to achieve a high degree of decoupling of the noisy signal. The experiments on real-world datasets demonstrate the effectiveness and efficiency of the proposed approach.This paper proposes END4Rec, a method for efficient noise-decoupling in multi-behavior sequential recommendation. The main contributions include: (1) Introducing an Efficient Behavior Sequence Miner (EBM) that captures complex user patterns with low computational cost. (2) Designing a Behavior-Aware Denoising module with Hard Noise Eliminator and Soft Noise Filter to effectively remove noise from user behavior data. (3) Introducing Noise-Decoupling Contrastive Learning and a guided training strategy to achieve effective noise removal and enhance the decoupling of noise signals. (4) Conducting comprehensive experiments on three real-world datasets, demonstrating the effectiveness and efficiency of END4Rec in handling multi-behavior sequential recommendation. The method addresses the challenges of efficiently mining user behavior sequences and reducing noise signals in multi-behavior sequential recommendation. The EBM module efficiently captures intricate patterns in user behavior while maintaining low time complexity and parameter count. The Behavior-Aware Denoising module includes Hard Noise Eliminator and Soft Noise Filter to remove different types of noise. The Noise-Decoupling Contrastive Learning and guided training strategy are used to contrast valid information with noisy signals and seamlessly integrate the two denoising processes to achieve a high degree of decoupling of the noisy signal. The experiments on real-world datasets demonstrate the effectiveness and efficiency of the proposed approach.