用大模型提升小米智能家居操作推荐精准度。
DevPiolt: Operation Recommendation for IoT Devices at Xiaomi Home
- 基于大模型持续预训练与多任务微调，注入物联网操作知识
- 通过偏好优化对齐用户习惯，提升推荐个性化程度
- 引入置信度控制机制，避免低质量推荐影响体验
物联网设备的操作推荐旨在根据用户上下文（如历史操作、环境信息、设备状态）生成个性化操作建议，对提升用户体验和企业收益至关重要。现有推荐模型在处理复杂操作逻辑、用户偏好多样性及对劣质建议敏感方面存在局限。为此，我们提出 DevPiolt，一种基于大语言模型的物联网设备操作推荐系统。首先，通过持续预训练和多任务微调，将基础物联网操作知识注入 LLM；其次，采用直接偏好优化使微调后的 LLM 与特定用户偏好对齐；最后，设计基于置信度的暴露控制机制，防止低质量推荐造成负面体验。大量实验表明，DevPiolt 在所有数据集上均显著优于基线模型，平均性能提升 69.5%。该模型已在小米家庭应用中上线运行一个季度，日均服务 25.5 万用户。线上实验结果显示，独立访问用户设备覆盖率提升 21.6%，页面浏览接受率提升 29.1%。
原文摘要 · Abstract (English)
Operation recommendation for IoT devices refers to generating personalized device operations for users based on their context, such as historical operations, environment information, and device status. This task is crucial for enhancing user satisfaction and corporate profits. Existing recommendation models struggle with complex operation logic, diverse user preferences, and sensitive to suboptimal suggestions, limiting their applicability to IoT device operations. To address these issues, we propose DevPiolt, a LLM-based recommendation model for IoT device operations. Specifically, we first equip the LLM with fundamental domain knowledge of IoT operations via continual pre-training and multi-task fine-tuning. Then, we employ direct preference optimization to align the fine-tuned LLM with specific user preferences. Finally, we design a confidence-based exposure control mechanism to avoid negative user experiences from low-quality recommendations. Extensive experiments show that DevPiolt significantly outperforms baselines on all datasets, with an average improvement of 69.5% across all metrics. DevPiolt has been practically deployed in Xiaomi Home app for one quarter, providing daily operation recommendations to 255,000 users. Online experiment results indicate a 21.6% increase in unique visitor device coverage and a 29.1% increase in page view acceptance rates.
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。