Academic Journal of Computing & Information Science, 2026, 9(6); doi: 10.25236/AJCIS.2026.090603.
Liu Liqun, Luo Jianhua, Zhang Xuting, Zhong Xiaorong, Xiao Yixuan, Qian Shuyan
School of Information Engineering, Guilin University, Guilin, Guangxi, China
To address reliance on manual experience for monthan persimmon disease identification, fragmented agricultural knowledge access, and inadequate grassroots service response, this paper designs and implements the "Sentinel in Persimmon Industry" multimodal intelligent service system. The system adopts front-end/back-end separation with layered decoupling: TypeScript and Vite for the front-end, Node.js and Express for business scheduling, Python and FastAPI for independent model inference, and MySQL for persistence. It integrates computer vision and natural language processing to provide intelligent leaf disease recognition, dual-channel Q&A (local knowledge base plus large language model), structured agricultural knowledge services, and operational data visualization, with automatic degradation and exception tolerance. Services are differentiated for growers, grassroots technicians, and administrators. Tests confirm complete functionality, stable operation, and good fault tolerance, offering a feasible solution for "AI + characteristic agriculture."
monthan persimmon disease recognition; deep learning; intelligent Q&A; multimodal fusion; knowledge service; smart agriculture
Liu Liqun, Luo Jianhua, Zhang Xuting, Zhong Xiaorong, Xiao Yixuan, Qian Shuyan. Sentinel in Persimmon Industry — A Multimodal Intelligent Service System for Persimmon Diseases Based on Deep Learning and Large Model Technology. Academic Journal of Computing & Information Science (2026), Vol. 9, Issue 6: 15-22. https://doi.org/10.25236/AJCIS.2026.090603.
[1] Li Yanmei, Zhou Wenxue, Wang Zhaoqi. Image recognition of pepper diseases and pests based on improved ResNet34 [J]. Journal of Jilin University (Science Edition), 2026. DOI:10.13413/j.cnki.jdxblxb.2025177.
[2] Fang Yingying, Pan Yanhong, Pan Xinling, et al. Design of crop disease and pest recognition system based on deep learning [J]. Journal of Smart Agriculture, 2026, 6(3): 23-28.
[3] Wang Liang, Zhang Qiang, Wei Yunxiao. Research on construction technology of intelligent question answering system based on knowledge base [J]. Network Security and Data Governance, 2026, 45(4): 68-73.
[4] Hu Yan. Forest and agricultural pest identification system based on deep learning and large model technology [J]. Popular Standardization, 2025(18): 36-38.
[5] Liang Zhongchao, Huang Qingbo. Guangxi Gongcheng: Creating a golden brand of monthan persimmon "billion-yuan industry" [N]. China Food News, 2025-12-10(002). DOI:10.28137/n.cnki.ncspb.2025.006467.
[6] Chen Nuo. Research on tobacco leaf disease and pest image recognition algorithm based on CNN [D]. Central South University of Forestry and Technology, 2025. DOI:10.27662/d.cnki.gznlc.2025.001402.
[7] Dong Wangyin, Fan Weiyang. Common disease and pest control measures for persimmon trees [J]. Modern Rural Science and Technology, 2025(09): 52-53.
[8] Liu Yuhai. Research and design of agricultural question answering system based on deep learning [D]. Sichuan Agricultural University, 2025. DOI:10.27345/d.cnki.gsnyu.2025.000854.
[9] Huang Yun. Research on the realization path of smart agriculture empowering Guangxi rural revitalization under the background of digital economy [J]. Journal of Smart Agriculture, 2024, 4(24): 5-8. DOI:10.20028/j.zhnydk.2024.24.002.
[10] Lu Y, Lu X, Zheng L, et al. Application of Multimodal Transformer Model in Intelligent Agricultural Disease Detection and Question-Answering Systems [J]. Plants, 2024, 13(7): 972. DOI:10.3390/plants13070972.