NGHIÊN CỨU GIẢI PHÁP KHUYẾN NGHỊ THÔNG MINH DỰA TRÊN SEMANTIC SIMILARITY VÀ PHÂN TÍCH NỘI DUNG

Tóm tắt

This study focuses on the development and evaluation of an intelligent recommendation solution based on semantic similarity and content analysis for product data. Instead of relying on traditional keyword-based search, the solution leverages vector embeddings to capture user intent and contextual meaning, thereby improving the accuracy of recommendations. Moreover, the approach combines semantic queries with content analysis to simulate the discovery of related products, enabling users to explore information in a natural and intuitive manner. Although implemented at a demo scale, the results demonstrate the potential of the model to be extended into personalized recommendation systems, trend prediction, and decision support applications. This work highlights the effectiveness of applying semantic similarity and content analysis in the development of modern recommendation models