Abstract: Recently, the recommendation method combined with Large Language Model has shown obvious advantages in improving recommendation accuracy and enhancing user experience. However, these methods do not make full use of user information, and cannot learn the behavioral characteristics of multiple user interactions by using only a single round of dialogue, and there are huge semantic differences between Large Language Models and recommender systems. In order to solve these problems, this thesis proposes a recommendation model based on the multi-round dialogue pattern of Large Language Model. The model uses vector quantization technology to convert user information into user indexes, and integrates the language semantics of the Large Language Model with the cooperative semantics of the recommender system through fine-tuning task, which not only learns the user characteristics but also alleviates the problem of semantic differences. The user index and historical interaction data are spliced into prompts, and then recommendations are fine-tuned through multiple rounds of dialogue mechanism to learn the characteristics between user interaction behaviors. The results show that the model is better than the comparison baseline algorithm in the two evaluation indexes of Hit Rate(HR) and Normalized Discounted Cumulative Gain(NDCG), and compared with the optimal comparison baseline algorithm on the two datasets, the average increase in HR is 10.53% and the average increase in NDCG is 5.01%, which proves the effectiveness of the model.

Key words: recommendation system, sequential recommendation, Large Language Models, multiple rounds of dialogue mechanisms

摘要： 最近结合大语言模型的推荐方法在提高推荐准确度和增强用户体验等方面展现出明显的优越性。然而这些方法存在没有充分利用用户信息、仅使用单轮对话无法学习用户多次交互的行为特征、大语言模型与推荐系统之间存在巨大的语义差异等问题。针对这些问题，本文提出了一个基于大语言模型多轮对话模式的推荐模型。该模型利用矢量量化技术将用户信息转化为用户索引，并通过微调任务把大语言模型的语言语义与推荐系统的协作语义整合，不仅学习了用户特征而且缓解了语义差异问题；将用户索引与历史交互数据拼接成提示语，再经过多轮对话机制进行推荐微调，从而学习用户交互行为之间的特征。模型在亚马逊Instructions、Arts和Games三个数据集上进行实验，结果表明模型在命中率（HR）和归一化折损累计增益（NDCG）两个评价指标上优于对比基线算法，在两个数据集上与最优对比基线算法相比，HR平均提升10.53%，NDCG平均提升5.01%，证明了模型的有效性。

关键词: 推荐系统, 序列推荐, 大语言模型, 多轮对话机制