When deep learning is applied to cervical cell screening, it encounters challenges related to the inefficient labeling of data and a shortage of annotators. To mitigate these challenges, this study introduces AL-Annotator, an active learning-based cervical cell annotation system. This system consists of three key components: an interactive interface designed for efficient pathologists’ review, a front-end and back-end separated cervical cell annotation system, and an active learning-based annotation method. Compared to traditional classification-based annotation methods, our annotation system achieves a 17.74% reduction in annotation quantity while improving the accuracy by 1.92%. This annotation system is crucial for developing and testing new machine learning and artificial intelligence algorithms for cervical screening, thereby facilitating advancements in diagnostic tools and methodologies.