Weblogs, comprised of records detailing user activities on any website, offer valuable insights into user preferences, behavior, and interests. Numerous recommendation algorithms, employing strategies such as collaborative filtering, content-based filtering, and hybrid methods, leverage the data mined through these weblogs to provide personalized recommendations to users. Despite the abundance of information available in these weblogs, identifying and extracting pertinent information and key features necessitates extensive engineering endeavors. The intricate nature of the data also poses a challenge for interpretation, especially for non-experts. In this study, we introduce a sophisticated and interactive recommendation framework denoted as InteraRec, which diverges from conventional approaches that exclusively depend on weblogs for recommendation generation. This framework captures high-frequency screenshots of web pages as users navigate through a website. Leveraging state-of-the-art multimodal large language models (MLLMs), it extracts valuable insights into user preferences from these screenshots by generating a user behavioral summary based on predefined keywords. Subsequently, this summary is utilized as input to an LLM-integrated optimization setup to generate tailored recommendations. Through our experiments, we demonstrate the effectiveness of InteraRec in providing users with valuable and personalized offerings.

翻译：网络日志由记录用户在任意网站上活动的详细数据构成，能够揭示用户偏好、行为及兴趣的宝贵信息。众多推荐算法（如协同过滤、基于内容的过滤及混合方法）通过挖掘这些日志数据为用户提供个性化推荐。尽管网络日志蕴含丰富信息，但识别并提取相关内容与关键特征仍需大量工程工作。数据的复杂性也使其解读面临挑战，尤其是对非专业人士而言。本研究提出一种新颖的交互式推荐框架InteraRec，它摒弃了传统仅依赖网络日志生成推荐的方法。该框架在用户浏览网站时捕获网页的高频截图，并利用最先进的多模态大语言模型（MLLMs）从这些截图中提取用户偏好的深度洞察，通过基于预定义关键词生成用户行为摘要。随后，该摘要作为输入传入集成大语言模型的优化模块，以生成定制化推荐。实验表明，InteraRec在为用户提供有价值且个性化的推荐方面具有显著有效性。