In the era of information explosion, as a form of personalized recommendation, dialogue recommendation systems provide users with personalized recommendation services through natural language interaction. However, in the face of complex user preferences, the traditional dialogue recommendation system has the problem of a poor recommendation effect. To solve these problems, this paper proposes a user preference dialogue recommendation algorithm (KGCR) based on a knowledge graph, which aims to enhance the understanding of user preferences through the semantic information of the knowledge graph and improve the relevance and accuracy of recommendations. This paper proposes a personalized conversation recommendation algorithm framework for user preference modeling. The framework uses a bilinear model attention mechanism and self-attention hierarchical coding structure to model user preferences to rank and recommend candidate items. By introducing rich user-related information, the recommendation results are not only more in line with users’ individual preferences but also have better diversity, effectively reducing the negative impact of information cocoons and other phenomena. At the same time, the experimental results on the open dataset prove the effectiveness and accuracy of the proposed model in the personalized conversation recommendation task.

This paper presents an optimized twin-tower model for text retrieval that addresses limitations in traditional models through improved feature interaction and loss function design. We introduce an early interaction layer using cross-attention mechanisms and a ranking-optimized loss function. These innovations enable earlier feature interactions between queries and documents, enhance semantic relationship understanding, and optimize relative similarity rankings while reducing overfitting risk. Our experiments on NQ, TQA, and WQ datasets show substantial Top-K accuracy improvements over benchmark models like BM25, DPR, ANCE, and ColBERT. For example, our model achieves a 20.3% relative improvement in Top-20 accuracy on NQ compared to BM25, with only 17 ms retrieval latency. Ablation studies confirm the effectiveness of our improvements. This research demonstrates that enhancing feature interaction and optimizing loss functions significantly improves twin-tower model performance, providing valuable methodological insights for efficient semantic retrieval while maintaining computational efficiency.