葡萄酒领域知识多路径检索增强生成方法优化研究

doi:10.3778/j.issn.1002-8331.2411-0470

摘要/Abstract

摘要： 在葡萄酒领域，设计专业的领域知识问答系统对于提升产区种植户、产业工人、酿酒师和品酒师的技术技能，以及助力整个产业的数字化转型具有重要意义。鉴于葡萄酒领域专业术语繁多、工艺细节庞杂、酒品分类多样、年份差异敏感以及酒庄文化异彩纷呈的特点，现有的智能问答系统往往因为信息提取不全和检索精度不足，导致回答的质量和准确性无法满足需求。提出了融合知识图谱、向量数据库和PKL文件库各自优势以构建葡萄酒领域知识库的方法，并探索了葡萄酒领域知识多路径检索增强生成方法（multi-path retrieval-augmented generation， MPRAG），通过并行检索不同路径，以提升检索结果的精准度和召回率。实验结果表明，MPRAG方法较目前多个开源RAG系统，在检索精准度和召回率指标上均提升了约20个百分点，可为葡萄酒领域的技术支持与人才培训提供支撑。

关键词: 多路径检索增强生成（MPRAG）, 智能问答系统, 低秩适应（LoRA）, 葡萄酒领域知识

Abstract: In the domain of wine, designing a specialized domain knowledge Q&A system is of great significance for improving the technical skills of vineyard growers, industry workers, winemakers, and sommeliers, as well as for supporting the digital transformation of the entire industry. Given the complexity of the wine domain, which involves a wide range of specialized terminology, intricate production processes, diverse wine classifications, sensitive vintage variations, and rich winery cultures, existing AI-powered Q&A systems often fall short due to incomplete information extraction and insufficient retrieval accuracy, failing to meet the quality and accuracy requirements of responses. A method is proposed, which integrates the strengths of knowledge graphs, vector databases, and PKL file libraries to construct a wine domain knowledge base. Additionally, the multi-path retrieval-augmented generation (MPRAG) method for wine domain knowledge is explored, which enhances the precision and recall of retrieval results through parallel retrieval across different paths. Experimental results indicate that the MPRAG method improves both precision and recall by approximately 20 percentage points compared to several existing open-source RAG systems, providing support for technical assistance and talent training in the wine industry.

Key words: multi-path retrieval-augmented generation (MPRAG), AI-powered Q&, A system, low-rank adaptation (LoRA), wine domain knowledge

杨文跃, 于千城, 王启明, 穆洪锐, 周诚辰. 葡萄酒领域知识多路径检索增强生成方法优化研究[J]. 计算机工程与应用, 2025, 61(22): 304-319.

YANG Wenyue, YU Qiancheng, WANG Qiming, MU Hongrui, ZHOU Chengchen. Optimization Research on Multi-Path Retrieval-Augmented Generation Method for Wine Domain Knowledge[J]. Computer Engineering and Applications, 2025, 61(22): 304-319.

参考文献

[1] 刘志林, 王磊, 丁银平, 等. 贺兰山东麓葡萄酒生产集群格局演变与驱动机制[J]. 经济地理, 2023, 43(8): 165-176.
LIU Z L, WANG L, DING Y P, et al. Spatiotemporal evolution of wine production clusters and its driving mechanism in the east of Helan Mountains[J]. Economic Geography, 2023, 43(8): 165-176.
[2] 黄天柱, 张欣悦, 薛春莉. 葡萄酒全产业链深度融合国际比较分析[J]. 中国酿造, 2023, 42(9): 240-245.
HUANG T Z, ZHANG X Y, XUE C L. International comparative analysis of the deep integration of the whole wine industry chain[J]. China Brewing, 2023, 42(9): 240-245.
[3] YANG X, CHEN A K, POURNEJATIAN N, et al. A large language model for electronic health records[J]. NPJ Digital Medicine, 2022, 5: 194.
[4] UBAH A E, ONAKPOJERUO E P, AJAMU J, et al. A review of artificial intelligence in education[C]//Proceedings of the 2022 International Conference on Artificial Intelligence of Things and Crowdsensing. Piscataway: IEEE, 2023: 38-45.
[5] 江双五, 张嘉玮, 华连生, 等. 基于大模型检索增强生成的气象数据库问答模型实现[J]. 计算机工程与应用, 2025, 61(5): 113-121.
JIANG S W, ZHANG J W, HUA L S, et al. Implementation of meteorological database question-answering based on large-scale model retrieval-augmentation generation[J]. Computer Engineering and Applications, 2025, 61(5): 113-121.
[6] CHARI S, ACHARYA P, GRUEN D M, et al. Informing clinical assessment by contextualizing post-hoc explanations of risk prediction models in type-2 diabetes[J]. Artificial Intelligence in Medicine, 2023, 137: 102498.
[7] ROUMELIOTIS K I, TSELIKAS N D. ChatGPT and open-AI models: a preliminary review[J]. Future Internet, 2023, 15(6): 192.
[8] DU Z X, QIAN Y J, LIU X, et al. GLM: general language model pretraining with autoregressive blank infilling[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Strou-dsburg: ACL, 2022: 320-335.
[9] JI S X, PAN S R, CAMBRIA E, et al. A survey on knowledge graphs: representation, acquisition, and applications[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(2): 494-514.
[10] PAN J J, WANG J G, LI G L. Survey of vector database man-agement systems[J]. The VLDB Journal, 2024, 33(5): 1591-1615.
[11] TANGMUNCHITTHAM E, PIROMSOPA K. An analysis of Python serialization towards distributed systems[C]//Proceedings of the 2022 19th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology. Piscataway: IEEE, 2022: 1-4.
[12] DEHGHAN M, ALOMRANI M, BAGGA S, et al. EWEK-QA: enhanced web and efficient knowledge graph retrieval for citation-based question answering systems[C]//Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stro-udsburg: ACL, 2024: 14169-14187.
[13] LEI Y B, DING L, CAO Y, et al. Unsupervised dense retrieval with relevance-aware contrastive pre-training[C]//Findings of the Association for Computational Linguistics: ACL 2023. Stroudsburg: ACL, 2023: 10932-10940.
[14] MA X G, FUN H, YIN X S, et al. Enhancing sparse retrieval via unsupervised learning[C]//Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region. New York: ACM, 2023: 150-157.
[15] DING N, QIN Y J, YANG G, et al. Parameter-efficient fine-tuning of large-scale pre-trained language models[J]. Nature Machine Intelligence, 2023, 5(3): 220-235.
[16] SUN Y, WANG S H, FENG S K, et al. ERNIE 3. 0: large-scale knowledge enhanced pre-training for language understanding and generation[J]. arXiv:2107.02137, 2017.
[17] BAI J Z, BAI S, CHU Y F, et al. Qwen technical report[J]. arXiv:2309.16609, 2023.
[18] XIAO J F, CHEN Y C, OU Y M, et al. Baichuan2-sum: ins-truction finetune Baichuan2-7B model for dialogue summarization[C]//Proceedings of the 2024 International Joint Conference on Neural Networks. Piscataway: IEEE, 2024: 1-8.
[19] 李凤英, 何晓蝶, 董荣胜. 融合语义信息的知识图谱多跳推理模型[J]. 模式识别与人工智能, 2022, 35(11): 1025-1032.
LI F Y, HE X D, DONG R S. Multi-hop inference model for knowledge graphs incorporating semantic information[J]. Pattern Recognition and Artificial Intelligence, 2022, 35(11): 1025-1032.
[20] 张元鸣, 姬琦, 徐雪松, 等. 基于知识图谱关系路径的多跳智能问答模型研究[J]. 电子学报, 2023, 51(11): 3092-3099.
ZHANG Y M, JI Q, XU X S, et al. Knowledge graph relation path network for multi-hop intelligent question answering[J]. Acta Electronica Sinica, 2023, 51(11): 3092-3099.
[21] FORMICA A, MELE I, TAGLINO F. A template-based approach for question answering over knowledge bases[J]. Knowledge and Information Systems, 2024, 66(1): 453-479.
[22] LAMANNA J A, MANGAN S A, ALONSO A, et al. Plant diversity increases with the strength of negative density dependence at the global scale[J]. Science, 2017, 356(6345): 1389-1392.
[23] CHEN Y R, LI H Y, HUA Y C, et al. Formal query building with query structure prediction for complex question ans-wering over knowledge base[C]//Proceedings of the 29th International Joint Conference on Artificial Intelligence, 2020: 3751-3758.
[24] GU Y, PAHUJA V, CHENG G, et al. Knowledge base question answering: a semantic parsing perspective[C]//Proceedings of the 4th Conference on Automated Knowledge Base Construction, 2022: 80-95.
[25] 高留杰, 赵文, 张君福, 等. G2S: 基于语义块的知识图谱问答语义解析[J]. 电子学报, 2021, 49(6): 1132-1141.
GAO L J, ZHAO W, ZHANG J F, et al. G2S: semantic segment based semantic parsing for question answering over knowledge graph[J]. Acta Electronica Sinica, 2021, 49(6): 1132-1141.
[26] ABDELAZIZ I, RAVISHANKAR S, KAPANIPATHI P, et al. A semantic parsing and reasoning-based approach to knowledge base question answering[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(18): 15985-15987.
[27] NI J J, YOUNG T, PANDELEA V, et al. Recent advances in deep learning based dialogue systems: a systematic survey[J]. Artificial Intelligence Review, 2023, 56(4): 3055-3155.
[28] YASUNAGA M, REN H Y, BOSSELUT A, et al. QA-GNN: reasoning with language models and knowledge graphs for question answering[C]//Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: ACL, 2021: 535-546.
[29] AHMADIAN M, AHMADI M, AHMADIAN S. A reliable deep representation learning to improve trust-aware recommendation systems[J]. Expert Systems with Applications, 2022, 197: 116697.
[30] LAN Y S, HE G L, JIANG J H, et al. A survey on complex knowledge base question answering: methods, challenges and solutions[C]//Proceedings of the 30th International Joint Conference on Artificial Intelligence, 2021: 4483-4491.
[31] ZHOU X H, SUN Z Y, LI G L. DB-GPT: large language model meets database[J]. Data Science and Engineering, 2024, 9(1): 102-111.
[32] XIAO S T, LIU Z, ZHANG P T, et al. C-pack: packed res-ources for general Chinese embeddings[C]//Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2024: 641-649.
[33] YU Y, YANG C H, KOLEHMAINEN J, et al. Low-rank adaptation of large language model rescoring for parameter-efficient speech recognition[C]//Proceedings of the 2023 IEEE Automatic Speech Recognition and Understanding Workshop. Piscataway: IEEE, 2024: 1-8.
[34] ZHENG Y W, ZHANG R C, ZHANG J H, et al. LlamaFactory: unified efficient fine-tuning of 100+ language models[C]//Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). Stroudsburg: ACL, 2024: 400-410.
[35] ES S, JAMES J, ESPINOSA ANKE L, et al. RAGAs: automated evaluation of retrieval augmented generation[C]//Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations. Stroudsburg: ACL, 2024: 150-158.
[36] ZHANG T Y, KISHORE V, WU F, et al. BERTScore: evaluating text generation with BERT[C]//Proceedings of the 8th International Conference on Learning Representations, 2020: 1-43.