TFHA: A Time–Frequency Harmonic Attention Framework for Analyzing Digital Management Strategy Impact Mechanisms

In the era of digital transformation, understanding and quantifying the mechanisms by which management strategies influence organizational performance is a critical yet insufficiently addressed challenge. Existing analytical models often overlook the intertwined temporal dependencies, cross-frequency interactions, and heterogeneous contextual factors that shape strategic impacts in real-world settings. To address these limitations, we propose TFHA (Time–Frequency Harmonic Attention), a unified framework that integrates frequency-domain pattern decomposition, temporal context encoding, and multi-view representation learning to analyze and forecast strategy-driven performance outcomes in an interpretable manner. Specifically, a Fourier Frequency Attention module captures multi-scale periodic patterns underlying strategic behaviors, while a temporal feature embedding component encodes both static calendar effects and dynamic, event-triggered fluctuations. Furthermore, a Contrastive Time–Frequency Representation Enhancement module aligns semantic, behavioral, and quantitative perspectives to produce robust, context-aware representations. Experiments on four real-world datasets from digital tourism management platforms demonstrate that TFHA reduces MAE by up to 18.5% compared with strong baselines such as Autoformer, Informer, and ETSformer, while exhibiting strong robustness under input perturbations and cross-domain generalization. These results highlight TFHA’s potential as both a predictive tool and an analytical lens for revealing the time–frequency dynamics underpinning the effectiveness of digital brand management strategies in tourism contexts.