Industrial recommender systems increasingly adopt multi-scenario learning (MSL) and multi-task learning (MTL) to handle diverse user interactions and contexts, but existing approaches suffer from two critical drawbacks: (1) underutilization of large-scale model parameters due to limited interaction with complex feature modules, and (2) difficulty in jointly modeling scenario and task information in a unified framework. To address these challenges, we propose a unified \textbf{M}ulti-\textbf{D}istribution \textbf{L}earning (MDL) framework, inspired by the "prompting" paradigm in large language models (LLMs). MDL treats scenario and task information as specialized tokens rather than auxiliary inputs or gating signals. Specifically, we introduce a unified information tokenization module that transforms features, scenarios, and tasks into a unified tokenized format. To facilitate deep interaction, we design three synergistic mechanisms: (1) feature token self-attention for rich feature interactions, (2) domain-feature attention for scenario/task-adaptive feature activation, and (3) domain-fused aggregation for joint distribution prediction. By stacking these interactions, MDL enables scenario and task information to "prompt" and activate the model's vast parameter space in a bottom-up, layer-wise manner. Extensive experiments on real-world industrial datasets demonstrate that MDL significantly outperforms state-of-the-art MSL and MTL baselines. Online A/B testing on Douyin Search platform over one month yields +0.0626\% improvement in LT30 and -0.3267\% reduction in change query rate. MDL has been fully deployed in production, serving hundreds of millions of users daily.

翻译：工业推荐系统日益采用多场景学习（MSL）与多任务学习（MTL）以处理多样化的用户交互与上下文，但现有方法存在两个关键缺陷：（1）由于与复杂特征模块的交互有限，导致大规模模型参数未得到充分利用；（2）难以在统一框架中联合建模场景与任务信息。为应对这些挑战，受大语言模型（LLMs）中“提示”范式的启发，我们提出了一种统一的**多分布学习**（MDL）框架。MDL将场景与任务信息视为专用标记而非辅助输入或门控信号。具体而言，我们设计了一个统一信息标记化模块，将特征、场景及任务转化为统一的标记格式。为促进深度交互，我们构建了三种协同机制：（1）特征标记自注意力以实现丰富特征交互；（2）领域-特征注意力用于场景/任务自适应特征激活；（3）领域融合聚合用于联合分布预测。通过堆叠这些交互层，MDL使场景与任务信息能够以自底向上、逐层递进的方式“提示”并激活模型的庞大参数空间。在真实工业数据集上的大量实验表明，MDL显著优于当前最先进的MSL与MTL基线方法。在抖音搜索平台为期一个月的在线A/B测试中，LT30指标提升+0.0626%，换词率降低-0.3267%。MDL现已全面部署于生产环境，每日服务数亿用户。