CTR prediction plays a vital role in recommender systems. Recently, large language models (LLMs) have been applied in recommender systems due to their emergence abilities. While leveraging semantic information from LLMs has shown some improvements in the performance of recommender systems, two notable limitations persist in these studies. First, LLM-enhanced recommender systems encounter challenges in extracting valuable information from lifelong user behavior sequences within textual contexts for recommendation tasks. Second, the inherent variability in human behaviors leads to a constant stream of new behaviors and irregularly fluctuating user interests. This characteristic imposes two significant challenges on existing models. On the one hand, it presents difficulties for LLMs in effectively capturing the dynamic shifts in user interests within these sequences, and on the other hand, there exists the issue of substantial computational overhead if the LLMs necessitate recurrent calls upon each update to the user sequences. In this work, we propose Lifelong User Behavior Modeling (LIBER) based on large language models, which includes three modules: (1) User Behavior Streaming Partition (UBSP), (2) User Interest Learning (UIL), and (3) User Interest Fusion (UIF). Initially, UBSP is employed to condense lengthy user behavior sequences into shorter partitions in an incremental paradigm, facilitating more efficient processing. Subsequently, UIL leverages LLMs in a cascading way to infer insights from these partitions. Finally, UIF integrates the textual outputs generated by the aforementioned processes to construct a comprehensive representation, which can be incorporated by any recommendation model to enhance performance. LIBER has been deployed on Huawei's music recommendation service and achieved substantial improvements in users' play count and play time by 3.01% and 7.69%.

翻译：点击率（CTR）预测在推荐系统中起着至关重要的作用。近年来，随着大语言模型（LLMs）涌现能力的出现，它们已被应用于推荐系统。尽管利用LLMs的语义信息已显示出对推荐系统性能的一些提升，但这些研究仍存在两个显著的局限性。首先，LLM增强的推荐系统在从文本语境中的终身用户行为序列中提取有价值信息以用于推荐任务方面面临挑战。其次，人类行为固有的可变性导致新行为不断涌现以及用户兴趣不规则地波动。这一特性给现有模型带来了两个重大挑战。一方面，这使得LLMs难以有效捕捉这些序列中用户兴趣的动态变化；另一方面，如果LLMs需要在用户序列每次更新时反复调用，则存在巨大的计算开销问题。在本工作中，我们提出了基于大语言模型的终身用户行为建模（LIBER），它包含三个模块：（1）用户行为流式分区（UBSP）、（2）用户兴趣学习（UIL）以及（3）用户兴趣融合（UIF）。首先，UBSP以增量范式将冗长的用户行为序列压缩为更短的分区，以促进更高效的处理。随后，UIL以级联方式利用LLMs从这些分区中推断洞察。最后，UIF整合上述过程生成的文本输出，构建一个全面的表征，该表征可以被任何推荐模型纳入以提升性能。LIBER已在华为的音乐推荐服务中部署，并在用户播放次数和播放时长上分别实现了3.01%和7.69%的显著提升。