解决多业务场景下生成式推荐的语义混淆与行为模式捕捉难题
MBGR: Multi-Business Prediction for Generative Recommendation at Meituan
- 引入业务感知的语义ID，按领域分词保留语义完整性
- 设计多业务预测结构，实现不同业务的独立生成能力
- 动态路由标签以增强稀疏多业务标签的表达能力，适合平台级推荐
生成式推荐（GR）作为工业推荐新范式，利用语义ID（SIDs）缩小编码解码空间，并基于下一词预测（NTP）探索规模效应。但现有方法在多业务场景中面临两大问题：一、NTP难以捕捉复杂跨业务行为模式，导致‘跷跷板现象’；二、统一语义ID空间引发表示混淆，无法区分各业务语义。为此，我们提出首个面向多业务场景的生成式推荐框架MBGR。其包含三大组件：首先，设计业务感知的语义ID（BID）模块，通过领域感知分词保持语义完整性；其次，引入多业务预测（MBP）结构，提供业务专属预测能力；最后，开发标签动态路由（LDR）模块，将稀疏多业务标签转换为稠密标签，进一步提升多业务生成能力。在美团外卖平台的离线与在线实验验证了MBGR的有效性，已成功投入生产。
原文摘要 · Abstract (English)
Generative recommendation (GR) has recently emerged as a promising paradigm for industrial recommendations. GR leverages Semantic IDs (SIDs) to reduce the encoding-decoding space and employs the Next Token Prediction (NTP) framework to explore scaling laws. However, existing GR methods suffer from two critical issues: (1) a \textbf{seesaw phenomenon} in multi-business scenarios arises due to NTP's inability to capture complex cross-business behavioral patterns; and (2) a unified SID space causes \textbf{representation confusion} by failing to distinguish distinct semantic information across businesses. To address these issues, we propose Multi-Business Generative Recommendation (MBGR), the first GR framework tailored for multi-business scenarios. Our framework comprises three key components. First, we design a Business-aware semantic ID (BID) module that preserves semantic integrity via domain-aware tokenization. Then, we introduce a Multi-Business Prediction (MBP) structure to provide business-specific prediction capabilities. Furthermore, we develop a Label Dynamic Routing (LDR) module that transforms sparse multi-business labels into dense labels to further enhance the multi-business generation capability. Extensive offline and online experiments on Meituan's food delivery platform validate MBGR's effectiveness, and we have successfully deployed it in production.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。