由于电商平台蔬菜产品信息繁杂且用户偏好多变,导致推荐匹配度较低。为了解决上述问题,提出基于协同过滤的电商平台蔬菜产品信息智能推荐方法。通过分析电商平台用户的购买历史和浏览行为,利用slope one方法和熵权法构建用户兴趣模型,深入理解了用户的蔬菜偏好和需求。采用协同过滤算法,结合用户对产品的评分数据和行为数据,计算蔬菜产品之间的相似度,得到更精准的产品关联信息。基于Spark平台,实现电商并行化协同过滤推荐技术,高效地生成个性化的蔬菜产品信息智能推荐。实验结果表明,研究方法能够在多种实验场景下显著提升推荐匹配度,具有实际应用价值。Because the vegetable product information of e-commerce platform is complicated and the user’s preference is changeable, the recommendation matching degree is low. In order to solve the above problems, an intelligent recommendation method of vegetable product information on e-commerce platform based on collaborative filtering was proposed. By analyzing the purchase history and browsing behavior of e-commerce platform users, slope one method and entropy weight method are used to build user interest model, and the user’s vegetable preference and demand are deeply understood. The collaborative filtering algorithm was used to calculate the similarity between vegetable products by combining the user’s score data and behavior data to obtain more accurate product association information. Based on the Spark platform, it realizes the parallel collaborative filtering recommendation technology of e-commerce, and efficiently generates personalized intelligent recommendation of vegetable product information. The experimental results show that the proposed method can significantly improve the recommendation matching degree under various experimental scenarios, and has practical application value.
