A Knowledge Graph and Deep Learning-Based Semantic Recommendation Database System for Advertisement Retrieval and Personalization

Tangtang Wang; Kaijie Zhang; Kuangcong Liu

doi:10.63313/JCSFT.9073

Authors

Tangtang Wang The University of Hong Kong, Hong Kong, China Author
Kaijie Zhang College of Engineering, Northeastern University, Boston, MA, USA Author
Kuangcong Liu Stanford University, Stanford, CA, USA Author

DOI:

https://doi.org/10.63313/JCSFT.9073

Keywords:

Knowledge Graph, Advertisement Recommendation, Deep Learning, Semantic Embedding, Vector Database, Graph Neural Network, Attention Mechanism

Abstract

In modern digital marketing, the growing complexity of advertisement data demands intelligent systems capable of understanding semantic relationships among products, audiences, and advertising content. To address this challenge, this paper proposes a Knowledge Graph and Deep Learning-Based Semantic Recommendation Database System (KGSR-ADS) for advertisement retrieval and personalization. The proposed framework integrates a heterogeneous Ad-Knowledge Graph (Ad-KG) that captures multi-relational semantics, a Semantic Embedding Layer that leverages large language models (LLMs) such as GPT and LLaMA to generate context-aware vector representations, a GNN + Attention Model that infers cross-entity dependencies, and a Database Optimization & Retrieval Layer based on vector indexing (FAISS/Milvus) for efficient semantic search. This layered architecture enables both accurate semantic matching and scalable retrieval, allowing personalized ad recommendations under large-scale heterogeneous workloads. Experiments were conducted on a large-scale real-world advertisement dataset containing approximately 1.2 million user profiles, 250,000 advertisements, and 20 million user-ad interactions. Experimental results demonstrate that the proposed KGSR-ADS model outperforms state-of-the-art baselines across all evaluation metrics. Compared with the strongest baseline GraphRec, KGSR-ADS achieves a 5.7% improvement in Precision@10, a 5.5% increase in Recall@10, a 6.3% gain in NDCG@10, and a 5.0% enhancement in MRR, while reducing average response latency by 23.9%. These results confirm the effectiveness and efficiency of integrating knowledge graph reasoning with semantic representation learning for personalized advertisement recommendation. These results demonstrate the system’s effectiveness and potential for next-generation semantic advertising platforms that integrate knowledge reasoning and deep learning for adaptive, real-time personalization.

References

[1] Liang T P, Yang Y F, Chen D N, et al. A semantic-expansion approach to personalized knowledge recommendation[J]. Decision Support Systems, 2008, 45(3): 401-412.

[2] Kanwal S, Nawaz S, Malik M K, et al. A review of text-based recommendation systems[J]. IEEE access, 2021, 9: 31638-31661.

[3] Gong J, Abhishek V, Li B. Examining the impact of keyword ambiguity on search advertising performance[J]. MIS Quarterly, 2018, 42(3): 805-A14.

[4] Gharibshah Z, Zhu X. User response prediction in online advertising[J]. aCM Computing Surveys (CSUR), 2021, 54(3): 1-43.

[5] Sharma A, Sharma A, Bose N, et al. Enhancing Personalized Advertising through Deep Reinforcement Learning and Natural Language Processing Techniques[J]. Innovative AI Research Journal, 2022, 11(10).

[6] Li, Zhenghang, Xinyu Li, and Xinning Lin. "Design and Implementation of a Platform for Business Intelligence Knowledge Mining and Graph Construction Based on Deep Learning." Proceedings of the 2nd International Symposium on Integrated Circuit Design and Integrated Systems. 2025.

[7] Shahbazi Z, Jalali R, Shahbazi Z. Enhancing Recommendation Systems with Real-Time Adaptive Learning and Multi-Domain Knowledge Graphs[J]. Big Data and Cognitive Computing, 2025, 9(5): 124.

[8] Wang H, Zhang F, Wang J, et al. Ripplenet: Propagating user preferences on the knowledge graph for recommender systems[C]//Proceedings of the 27th ACM international conference on information and knowledge management. 2018: 417-426.

[9] Chicaiza J, Valdiviezo-Diaz P. A comprehensive survey of knowledge graph-based recommender systems: Technologies, development, and contributions[J]. Information, 2021, 12(6): 232.

[10] Gao Y, Li Y F, Lin Y, et al. Deep learning on knowledge graph for recommender system: A survey[J]. arXiv preprint arXiv:2004.00387, 2020.

[11] Wu, Likang, et al. "A survey on large language models for recommendation." World Wide Web 27.5 (2024): 60.

[12] Zhang S, Zhang N, Fan S, et al. Knowledge graph recommendation model based on adversarial training[J]. Applied Sciences, 2022, 12(15): 7434.

[13] Zhang, Xuelian. "Graph Neural Network Knowledge Graph Recommendation Model Integrating Deep Domain Information and Important Domain Information." INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS, NETWORKING AND APPLICATIONS. Singapore: Springer Nature Singapore, 2023.

[14] Lin, Yuzhen, et al. "CEMG: Collaborative-Enhanced Multimodal Generative Recommendation." International Conference on Multimedia Modeling. Singapore: Springer Nature Singapore, 2026.

[15] Jiang, Gaozhe, et al. "Investment advisory robotics 2.0: Leveraging deep neural networks for personalized financial guidance." 2025 International Joint Conference on Neural Networks (IJCNN). IEEE, 2025.

[16] Luo, RuiHan, Nanxi Wang, and Xiaotong Zhu. "Fraud detection and risk assessment of online payment transactions on e-commerce platforms based on llm and gcn frameworks." arXiv preprint arXiv:2509.09928 (2025).