AI 中文总结
针对现有排序模型难以解耦结构化意图的问题，提出GateDiffInt框架，通过可控扩散与LLM蒸馏实现意图感知表示，在公开及工业数据集和线上测试中均取得显著效果。
AI 中文摘要
现有的排序模型仅隐式编码意图，难以解耦具有不同强度和时间尺度的结构化意图。行为序列中的噪声与意图相互强化，我们将此称为噪声-意图耦合（Noise--Intent Coupling, NIC）。噪声会稀释真实意图，而缺乏结构化意图先验会导致去噪缺乏明确的目标。为解决NIC问题，我们提出GateDiffInt，一种用于工业排序的意图交互框架。它利用最终转化信号共同对齐序列去噪与意图提取。GateDiffInt应用带双门控的可控前向扩散过程，以增强和去噪行为序列。随后，大语言模型作为教师模型，将四种结构化意图——长期、短期、潜在及转化意图——蒸馏至轻量学生模型中。增强后的序列与结构化意图表示通过注意力深度融合，生成用于转化率预测的意图感知表示。在公开及大规模工业数据集上的实验表明，该模型相比强基线取得了一致的提升。在服务数亿日活用户的在线A/B测试中，GateDiffInt实现了显著的GMV提升，并已部署至核心流量，验证了其有效性与生产就绪性。
英文摘要
Existing ranking models encode intent only implicitly, making it hard to disentangle structured intents of varying strength and temporal scale. Noise and intent in behavior sequences are mutually reinforcing---we call this Noise--Intent Coupling (NIC). Noise dilutes true intents, while the lack of structured intent priors leaves denoising without a clear target. To address NIC, we propose GateDiffInt, an intent interaction framework for industrial ranking. It uses the final conversion signal to jointly align sequence denoising and intent extraction. GateDiffInt applies a controllable forward diffusion process with dual gating to enhance and denoise behavior sequences. A large language model then acts as teacher to distill four structured intents---long-term, short-term, latent, and conversion into a lightweight student model. The enhanced sequence and structured intent representations are deeply fused via attention to produce intent-aware representations for conversion-rate prediction. Extensive experiments on public and large-scale industrial datasets show consistent gains over strong baselines. In online A/B tests serving hundreds of millions of daily active users, GateDiffInt delivers substantial GMV improvements and has been deployed to primary traffic, confirming both effectiveness and production readiness.
